CN114403889B - NN interval signal acquisition device, NN interval signal acquisition system and storage medium - Google Patents
NN interval signal acquisition device, NN interval signal acquisition system and storage medium Download PDFInfo
- Publication number
- CN114403889B CN114403889B CN202210249257.5A CN202210249257A CN114403889B CN 114403889 B CN114403889 B CN 114403889B CN 202210249257 A CN202210249257 A CN 202210249257A CN 114403889 B CN114403889 B CN 114403889B
- Authority
- CN
- China
- Prior art keywords
- sinus
- wave sequence
- wave
- determining
- interval
- 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.)
- Active
Links
- 239000006185 dispersion Substances 0.000 claims abstract description 51
- 239000012634 fragment Substances 0.000 claims description 44
- 230000011218 segmentation Effects 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 abstract description 14
- 238000009825 accumulation Methods 0.000 abstract description 5
- 238000012546 transfer Methods 0.000 abstract description 5
- 238000000034 method Methods 0.000 description 16
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 3
- 208000000418 Premature Cardiac Complexes Diseases 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002861 ventricular Effects 0.000 description 2
- 230000002567 autonomic effect Effects 0.000 description 1
- 210000003403 autonomic nervous system Anatomy 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 230000002123 temporal effect Effects 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
- A61B5/24—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
- A61B5/24—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]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
- A61B5/352—Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval
-
- 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]
- A61B5/346—Analysis of electrocardiograms
- A61B5/349—Detecting specific parameters of the electrocardiograph cycle
- A61B5/363—Detecting tachycardia or bradycardia
-
- 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)
- Cardiology (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses an NN interval signal acquisition device, an NN interval signal acquisition system and a storage medium. The invention acquires electrocardiosignals of a subject; determining a sinus R wave sequence and a non-sinus R wave sequence corresponding to the electrocardiosignal; determining sparsity and dispersion of the non-sinus R-wave sequence; judging whether the non-sinus R wave sequence meets a preset condition according to the sparsity and the dispersion; and when the non-sinus R wave sequence does not meet the preset condition, eliminating target R waves in the sinus R wave sequence according to the non-sinus R wave sequence to obtain NN interval signals. Compared with the existing mode of determining NN interval signals through time domain analysis and frequency domain analysis, the NN interval signal detection method and device based on the frequency domain analysis achieve end-to-end detection of NN intervals, avoid backward accumulation transfer of error rates, enable NN interval signals with fewer error rates to be obtained, and improve accuracy of follow-up HRV analysis.
Description
Technical Field
The invention relates to the technical field of QRS wave detection, in particular to an NN interval signal acquisition device, an NN interval signal acquisition system and a storage medium.
Background
Heart rate variability refers to the subtle temporal changes between successive cardiac cycles and their regularity, which are commonly used to evaluate the effects of the autonomic nervous system on the regulation of the heart, as an important noninvasive indicator of autonomic nervous activity. In the prior art, before analyzing the heart rhythm variability time domain and the frequency domain of an electrocardiogram, the artifact is required to be identified, R waves are searched, and then RR intervals are corrected to eliminate the RR intervals of non-sinus heart beats. At present, although the detection sensitivity and the positive predictive value of the R wave detection algorithm on standard electrocardiogram databases such as MIT-BIH and AHA are more than 99%, the recognition accuracy on noisy dynamic electrocardiograms is less than 80%. In addition, when the RR interval is corrected, the origin type of the heart beat needs to be identified first, and then a corresponding correction method is adopted for different heart beat types. In the heart beat detection algorithm in the current stage, the sensitivity of ventricular premature beat detection is generally lower than 80%, the positive predictive value is lower than 60%, and the sensitivity and the positive predictive value of ventricular premature beat are more than 80%. The current NN interval processing flow means that the false detection rate and the omission rate of the two processing flows are in a multiplication relationship, which means that the accuracy rate of the finally obtained NN interval may be less than 80%.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The invention mainly aims to provide an NN interval signal acquisition device, an NN interval signal acquisition system and a storage medium, and aims to solve the technical problem that NN interval signals confirmed by the prior art are low in accuracy.
To achieve the above object, the present invention provides an NN interval signal acquiring apparatus including: a memory, a processor, and an NN interval signal retrieval program stored on the memory and executable on the processor, the NN interval signal retrieval program configured to implement the steps of:
Acquiring an electrocardiosignal of a subject;
Determining a sinus R wave sequence and a non-sinus R wave sequence corresponding to the electrocardiosignal;
determining sparsity and dispersion of the non-sinus R-wave sequence;
judging whether the non-sinus R wave sequence meets a preset condition according to the sparsity and the dispersion;
And when the non-sinus R wave sequence does not meet the preset condition, eliminating target R waves in the sinus R wave sequence according to the non-sinus R wave sequence to obtain NN interval signals.
Optionally, when the non-sinus R-wave sequence does not meet the preset condition, determining R-waves adjacent to the non-sinus R-wave sequence in the sinus R-wave sequence;
selecting a preset number of R waves from the adjacent R waves as the target R waves, and eliminating the target R waves;
Dividing the sinus R wave sequence into a plurality of NN analysis fragments by taking the position of the target R wave as a dividing point;
and determining NN interval signals according to the NN analysis fragments.
Optionally, determining a target segment with a segment length smaller than a preset length in the NN analysis segment;
removing the target fragment from the NN analysis fragment to obtain a removed fragment;
and determining the NN interval signal according to the removed fragments.
Optionally, the sparsity of the non-sinus R-wave sequence is calculated according to the following formula:
Wherein spark (X) is used to characterize the sparseness of the non-sinus R wave sequence, # (X) is used to characterize the number of non-sinus R waves in the non-sinus R wave sequence, and # (Y) is used to characterize the number of sinus R waves in the sinus R wave sequence.
Optionally, the dispersion of the non-sinus R-wave sequence is calculated according to the following formula:
Wherein Dispersion (X) is used to characterize the Dispersion of the non-sinus R-wave sequence, max (X) is used to characterize the maximum value of R-wave positions in the non-sinus R-wave sequence, min (X) is used to characterize the minimum value of R-wave positions in the non-sinus R-wave sequence, leb (ecgsig) is used to characterize the length of the electrocardiograph signal, cv (X) is used to characterize the coefficient of variation of the non-sinus R-wave sequence.
Optionally, preprocessing the electrocardiosignal to obtain a tag sequence;
Inputting the electrocardiosignal and the tag sequence into a preset semantic segmentation prediction model to obtain an output result;
and determining a sinus R wave sequence and a non-sinus R wave sequence corresponding to the electrocardiosignal according to the output result.
Optionally, determining an RR interval of the electrocardiograph signal;
Determining a heart rate value sequence according to the RR interval;
Determining the size of a window according to the heart rate value sequence, and determining a target interval according to the size of the window;
And marking the R wave in the target interval to obtain a tag sequence.
Optionally, when the non-sinus R-wave sequence meets the preset condition, performing a difference operation on the sinus R-wave sequence according to a linear difference value or a cubic spline difference value.
In addition, to achieve the above object, the present invention also provides an NN interval signal acquisition system, including: the device comprises an acquisition module, an R wave sequence determination module, a sparsity and dispersion determination module, a judgment module and an NN interval signal determination module;
the acquisition module is used for acquiring electrocardiosignals of the subject;
the R wave sequence determining module is used for determining a sinus R wave sequence and a non-sinus R wave sequence corresponding to the electrocardiosignal;
the sparsity and dispersion determining module is used for determining the sparsity and dispersion of the non-sinus R wave sequence;
the judging module is used for judging whether the non-sinus R wave sequence meets a preset condition according to the sparsity and the dispersion;
And the NN interval signal determining module is used for eliminating target R waves in the sinus R wave sequence according to the non-sinus R wave sequence when the non-sinus R wave sequence does not meet the preset condition, so as to obtain an NN interval signal.
In addition, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon an NN interval signal acquisition program which, when executed by a processor, implements the steps of:
Acquiring an electrocardiosignal of a subject;
Determining a sinus R wave sequence and a non-sinus R wave sequence corresponding to the electrocardiosignal;
determining sparsity and dispersion of the non-sinus R-wave sequence;
judging whether the non-sinus R wave sequence meets a preset condition according to the sparsity and the dispersion;
And when the non-sinus R wave sequence does not meet the preset condition, eliminating target R waves in the sinus R wave sequence according to the non-sinus R wave sequence to obtain NN interval signals.
The invention acquires electrocardiosignals of a subject; determining a sinus R wave sequence and a non-sinus R wave sequence corresponding to the electrocardiosignal; determining sparsity and dispersion of the non-sinus R-wave sequence; judging whether the non-sinus R wave sequence meets a preset condition according to the sparsity and the dispersion; and when the non-sinus R wave sequence does not meet the preset condition, eliminating target R waves in the sinus R wave sequence according to the non-sinus R wave sequence to obtain NN interval signals. Compared with the existing mode of determining NN interval signals through time domain analysis and frequency domain analysis, the NN interval signal detection method and device based on the frequency domain analysis achieve end-to-end detection of NN intervals, avoid backward accumulation transfer of error rates, enable NN interval signals with fewer error rates to be obtained, and improve accuracy of follow-up HRV analysis.
Drawings
FIG. 1 is a schematic diagram of an NN interval signal acquisition apparatus of a hardware runtime environment in which embodiments of the present invention are implemented;
FIG. 2 is a flowchart of a NN interval signal acquiring apparatus according to a first embodiment of the present invention;
FIG. 3 is a schematic diagram showing the model output results of a first embodiment of the NN interval signal acquiring apparatus according to the present invention;
FIG. 4 is a flowchart of a NN interval signal acquiring apparatus according to a second embodiment of the invention;
FIG. 5 is a block diagram of a first embodiment of an NN interval signal in accordance with the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic diagram of an NN interval signal acquiring apparatus in a hardware running environment according to an embodiment of the present invention.
As shown in fig. 1, the NN interval signal acquiring apparatus may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (WI-FI) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Those skilled in the art will appreciate that the structure shown in fig. 1 does not constitute a limitation of the NN interval signal acquisition apparatus, and may include more or fewer components than shown, or certain components may be combined, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and an NN interval signal acquisition program may be included in the memory 1005 as one type of storage medium.
In the NN interval signal acquiring apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the NN interval signal acquiring apparatus calls an NN interval signal acquiring program stored in the memory 1005 through the processor 1001.
Referring to fig. 2, fig. 2 is a flowchart of a first embodiment of the NN interval signal acquiring apparatus according to the present invention.
The embodiment of the invention provides an NN interval signal acquisition device, which comprises: a memory, a processor, and an NN interval signal retrieval program stored on the memory and executable on the processor, the NN interval signal retrieval program configured to implement the steps of: in this embodiment, the NN interval signal acquiring apparatus includes the following steps:
Step S10: an electrocardiographic signal of the subject is acquired.
It should be noted that the subject may be a user who needs to detect their NN interval signals. The electrocardiographic signal may be an electrocardiographic signal of the subject.
Step S20: and determining a sinus R wave sequence and a non-sinus R wave sequence corresponding to the electrocardiosignal.
It should be noted that, the determining the sinus R-wave sequence and the non-sinus R-wave sequence corresponding to the electrocardiograph signal may be determining the sinus R-wave sequence and the non-sinus R-wave sequence corresponding to the electrocardiograph signal according to a pre-trained semantic segmentation prediction model.
Further, in order to obtain a more accurate sinus R-wave sequence and a non-sinus R-wave sequence, the step S20 may include: preprocessing the electrocardiosignal to obtain a tag sequence; inputting the electrocardiosignal and the tag sequence into a preset semantic segmentation prediction model to obtain an output result; and determining a sinus R wave sequence and a non-sinus R wave sequence corresponding to the electrocardiosignal according to the output result.
It should be noted that, the preprocessing the electrocardiosignal to obtain a tag sequence may be determining an RR interval of the electrocardiosignal; determining a heart rate value sequence according to the RR interval; determining the size of a window according to the heart rate value sequence, and determining a target interval according to the size of the window; and marking the R wave in the target interval to obtain a tag sequence.
The determining the RR interval of the electrocardiograph signal may be determining an interval between R waves in the electrocardiograph signal, and the interval between R waves may be used as the RR interval. The determining the heart rate value sequence from the RR interval may be determining the heart rate value sequence from the following formula:
Wherein hr is used to characterize the heart rate value sequence and RR is used to characterize the RR interval sequence.
It should be noted that, the window size may be determined according to the following formula:
wherein the window is used for characterizing window size, and the mean () function is used for solving the mean value of the sequence of heart rate values.
It should be noted that, the determining the target interval according to the window size may be to record the current R wave position as R, record the interval [ R-0.105 x window, r+0.15 x window ] as the target interval, re-label the points in the target interval, if the R wave is a sinus R wave, label all the points in the range with label 2, if the R wave is a non-sinus R wave, a spot within this range is labeled 1, if the R wave is neither a sinus R wave nor a non-sinus R wave, the spots within this range are marked with the label 0, and after the above-mentioned treatment, a tag sequence (0..1..2..1..1..0..0..2..2..the following format was obtained)
It should be noted that, the inputting the electrocardiograph signal and the tag sequence to the preset semantic segmentation prediction model may be obtaining an output result by cutting the electrocardiograph signal into a signal with a preset length and inputting the tag sequence to the preset semantic segmentation prediction model. The preset semantic segmentation prediction model may be a pre-trained model capable of predicting whether the electrocardiosignal is a sinus R wave or a non-sinus R wave. The cutting the electrocardiosignal into a preset length may be cutting the electrocardiosignal into a 1 minute section.
In specific implementation, considering the unbalance of categories and different training difficulty, we use the following equation based on the Batch-Weighted loss function:
Wherein Loss is used for identifying a Loss function during model training, y i is used for representing the ith data input into a preset semantic segmentation prediction model for training, Used for representing the predictive probability value output by the model during the last training, gamma used for representing the modulation coefficient which is more than or equal to 0 and used for adjusting the difficulty degree of category learning,The closer to 1 the easier it is to learn,The weight of the easy-to-learn sample can be reduced at an exponential rate, so that the model can concentrate on the class difficult to learn, lambda is used to characterize the weight decay factor,For characterizing the L2 regularization term,Wherein,The method is used for representing the weight of the loss function of the ith batch, M is the size of the batch, epsilon takes a minimum value, and the condition that the weight is 0 when only one type of batch appears in a certain batch is avoided. I is an indicator function or an indicator function.
In a specific implementation, the output result of the preset semantic segmentation prediction model may be shown in fig. 3, where fig. 3 is a schematic diagram of the model output result of the first embodiment of the NN interval signal acquiring apparatus according to the present invention, where 100 is used to characterize an original electrocardiographic signal, 200 is a tag sequence after preprocessing, and 300 is the output result of the preset semantic segmentation prediction model.
Step S30: sparsity and dispersion of the non-sinus R-wave sequence are determined.
It should be noted that, the determining the sparseness of the non-sinus R-wave sequence may be determining the sparseness of the non-sinus R-wave sequence according to the following formula:
Wherein spark (X) is used to characterize the sparseness of the non-sinus R wave sequence, # (X) is used to characterize the number of non-sinus R waves in the non-sinus R wave sequence, and # (Y) is used to characterize the number of sinus R waves in the sinus R wave sequence.
The number of non-sinus R waves in the non-sinus R wave sequence may be the number of all non-sinus R waves in the non-sinus R wave sequence belonging to the electrocardiograph signal. For example, there are 8 non-sinus R-wave sequences, and the number of non-sinus R-waves included in the non-sinus R-wave sequences is 2,1,3,5,4,3,2,2, respectively, and the number of non-sinus R-waves in the non-sinus R-wave sequences is 22. The number of sinus R waves is the same, and this embodiment will not be described here again.
It should be noted that, the determining the dispersion of the non-sinus R-wave sequence may be determining the dispersion of the non-sinus R-wave sequence according to the following formula:
Wherein Dispersion (X) is used to characterize the Dispersion of the non-sinus R-wave sequence, max (X) is used to characterize the maximum value of R-wave position in the non-sinus R-wave sequence, min (X) is used to characterize the minimum value of R-wave position in the non-sinus R-wave sequence, len (ecgsig) is used to characterize the length of the electrocardiograph signal, cv (X) is used to characterize the coefficient of variation of the non-sinus R-wave sequence.
The coefficient of variation may be a user-set coefficient of variation.
Step S40: judging whether the non-sinus R wave sequence meets a preset condition according to the sparsity and the dispersion.
It should be noted that, the preset condition may be to obtain a preset sparsity threshold and a dispersion threshold, and the preset condition may be that the sparsity of the non-sinus R-wave sequence is greater than the sparsity threshold or the dispersion is less than the dispersion threshold. The determining whether the non-sinus R-wave sequence meets a preset condition according to the sparseness and the dispersion may be determining whether the sparseness of the non-sinus R-wave sequence is greater than the sparseness threshold or whether the dispersion is less than the dispersion threshold.
Step S50: and when the non-sinus R wave sequence does not meet the preset condition, eliminating target R waves in the sinus R wave sequence according to the non-sinus R wave sequence to obtain NN interval signals.
The removing the target R wave in the sinus R wave sequence according to the non-sinus R wave sequence may be removing two front and back adjacent to the non-sinus R wave in the sinus R wave sequence, and obtaining the NN interval signal may be removing four R waves in total.
Further, NN interval signals are obtained for accuracy. After the step S40, the method further includes: and when the non-sinus R wave sequence meets the preset condition, performing difference operation on the sinus R wave sequence according to a linear difference value or a cubic spline difference value.
It should be noted that the linear difference or the cubic spline difference may be a difference in the prior art, which is not described herein in detail.
The embodiment acquires an electrocardiosignal of a subject; determining a sinus R wave sequence and a non-sinus R wave sequence corresponding to the electrocardiosignal; determining sparsity and dispersion of the non-sinus R-wave sequence; judging whether the non-sinus R wave sequence meets a preset condition according to the sparsity and the dispersion; and when the non-sinus R wave sequence does not meet the preset condition, eliminating target R waves in the sinus R wave sequence according to the non-sinus R wave sequence to obtain NN interval signals. Compared with the existing mode of determining NN interval signals through time domain analysis and frequency domain analysis, the mode of the embodiment realizes end-to-end detection of NN intervals, avoids backward accumulation transfer of error rates, enables NN interval signals with fewer error rates to be obtained, and improves accuracy of subsequent HRV analysis.
Referring to fig. 4, fig. 4 is a flowchart illustrating a second embodiment of the NN interval signal acquiring apparatus according to the present invention.
Based on the first embodiment, in this embodiment, the step S50 may include:
step S501: and when the non-sinus R wave sequence does not meet the preset condition, determining R waves adjacent to the non-sinus R wave sequence in the sinus R wave sequence.
Step S502: selecting a preset number of R waves from the adjacent R waves as the target R waves, and eliminating the target R waves.
It should be noted that the preset number may be a preset number to be removed, for example, two R waves, in front and back, adjacent to a non-sinus R wave in the sinus R wave removing sequence, total four R waves, and the removed four R waves are the target R waves. The R-waves adjacent to the non-sinus R-waves in the sinus R-wave sequence may be eliminated, and the embodiment is not limited herein.
Step S503: and dividing the sinus R wave sequence into a plurality of NN analysis fragments by taking the position of the target R wave as a dividing point.
It should be noted that, the dividing the sinus R wave sequence into the plurality of NN analysis segments may be by taking the target R wave as a dividing point, and dividing the sinus R wave sequence into the plurality of segments, that is, the NN analysis segments.
Step S504: and determining NN interval signals according to the NN analysis fragments.
It should be noted that, the determining the NN interval signal according to the NN analysis fragment may be determining a target fragment with a fragment length smaller than a preset length in the NN analysis fragment; removing the target fragment from the NN analysis fragment to obtain a removed fragment; and determining the NN interval signal according to the removed fragments.
It should be noted that the preset length may be a length of the acquired segment corresponding to a time of 1 minute. The determining the target fragment with the fragment length smaller than the preset length in the NN analysis fragment may include taking the fragment length with the fragment length smaller than 1 minute in the NN analysis fragment as the target fragment. The determining the NN interval signal according to the removed segment may include taking the NN analysis segment remaining after the removal of the target segment as the NN interval signal.
When the non-sinus R-wave sequence does not meet the preset condition, determining R-waves adjacent to the non-sinus R-wave sequence in the sinus R-wave sequence; selecting a preset number of R waves from the adjacent R waves as the target R waves, and eliminating the target R waves; dividing the sinus R wave sequence into a plurality of NN analysis fragments by taking the position of the target R wave as a dividing point; and determining NN interval signals according to the NN analysis fragments. The embodiment converts the original difficult filtering and R wave detection into relatively easy sinus R wave, non-sinus R wave and non-R wave classification problems. The end-to-end detection of NN intervals is realized, the backward accumulation transfer of error rates is avoided, NN sequences with fewer error rates can be obtained, and the accuracy of subsequent HRV analysis is improved.
Referring to fig. 5, fig. 5 is a block diagram illustrating a first embodiment of the NN interval signal acquiring system according to the present invention.
As shown in fig. 5, the NN interval signal acquisition system according to the embodiment of the present invention includes: the device comprises an acquisition module 10, an R-wave sequence determination module 20, a sparsity and dispersion determination module 30, a judgment module 40 and an NN interval signal determination module 50;
an acquisition module 10 for acquiring an electrocardiographic signal of a subject;
An R-wave sequence determining module 20, configured to determine a sinus R-wave sequence and a non-sinus R-wave sequence corresponding to the electrocardiographic signal;
a sparsity and dispersion determination module 30 for determining sparsity and dispersion of the non-sinus R-wave sequence;
A judging module 40, configured to judge whether the non-sinus R-wave sequence meets a preset condition according to the sparsity and the dispersion;
And the NN interval signal determining module 50 is configured to, when the non-sinus R wave sequence does not meet the preset condition, reject a target R wave in the sinus R wave sequence according to the non-sinus R wave sequence, and obtain an NN interval signal.
The embodiment acquires an electrocardiosignal of a subject; determining a sinus R wave sequence and a non-sinus R wave sequence corresponding to the electrocardiosignal; determining sparsity and dispersion of the non-sinus R-wave sequence; judging whether the non-sinus R wave sequence meets a preset condition according to the sparsity and the dispersion; and when the non-sinus R wave sequence does not meet the preset condition, eliminating target R waves in the sinus R wave sequence according to the non-sinus R wave sequence to obtain NN interval signals. Compared with the existing mode of determining NN interval signals through time domain analysis and frequency domain analysis, the mode of the embodiment realizes end-to-end detection of NN intervals, avoids backward accumulation transfer of error rates, enables NN interval signals with fewer error rates to be obtained, and improves accuracy of subsequent HRV analysis.
It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
In addition, technical details that are not described in detail in this embodiment may refer to the parameter operation method provided in any embodiment of the present invention, and are not described herein again.
Based on the first embodiment of the NN interval signal acquiring system of the present invention, a second embodiment of the NN interval signal acquiring system of the present invention is proposed.
In this embodiment, the NN interval signal determining module 50 is further configured to determine R waves adjacent to the non-sinus R wave sequence in the sinus R wave sequence when the non-sinus R wave sequence does not meet the preset condition; selecting a preset number of R waves from the adjacent R waves as the target R waves, and eliminating the target R waves; dividing the sinus R wave sequence into a plurality of NN analysis fragments by taking the position of the target R wave as a dividing point; and determining NN interval signals according to the NN analysis fragments.
Further, the NN interval signal determining module 50 is further configured to determine a target segment with a segment length smaller than a preset length in the NN analysis segment; removing the target fragment from the NN analysis fragment to obtain a removed fragment; and determining the NN interval signal according to the removed fragments.
Further, the sparsity and dispersion determining module 30 is further configured to calculate the sparsity of the non-sinus R-wave sequence according to the following formula:
Wherein spark (X) is used to characterize the sparseness of the non-sinus R wave sequence, # (X) is used to characterize the number of non-sinus R waves in the non-sinus R wave sequence, and # (Y) is used to characterize the number of sinus R waves in the sinus R wave sequence.
Further, the sparsity and dispersion determining module 30 is further configured to calculate the dispersion of the non-sinus R-wave sequence according to the following formula:
wherein Dispersion (X) is used to characterize the Dispersion of the non-sinus R-wave sequence, max (X) is used to characterize the maximum value of R-wave position in the non-sinus R-wave sequence, min (X) is used to characterize the minimum value of R-wave position in the non-sinus R-wave sequence, len (ecgsig) is used to characterize the length of the electrocardiograph signal, cv (X) is used to characterize the coefficient of variation of the non-sinus R-wave sequence.
Further, the R-wave sequence determining module 20 is further configured to pre-process the electrocardiograph signal to obtain a tag sequence; inputting the electrocardiosignal and the tag sequence into a preset semantic segmentation prediction model to obtain an output result; and determining a sinus R wave sequence and a non-sinus R wave sequence corresponding to the electrocardiosignal according to the output result.
Further, the R-wave sequence determining module 20 is further configured to determine an RR interval of the electrocardiograph signal; determining a heart rate value sequence according to the RR interval; determining the size of a window according to the heart rate value sequence, and determining a target interval according to the size of the window; and marking the R wave in the target interval to obtain a tag sequence.
Further, the judging module 40 is further configured to perform a difference operation on the sinus R-wave sequence according to a linear difference or a cubic spline difference when the non-sinus R-wave sequence meets the preset condition.
Other embodiments or specific implementations of the NN interval signal acquisition system of the present invention may refer to the above-mentioned method embodiments, and are not described herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. read-only memory/random-access memory, magnetic disk, optical disk), comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (9)
1. An NN interval signal acquisition apparatus, characterized in that the NN interval signal acquisition apparatus includes: a memory, a processor, and an NN interval signal retrieval program stored on the memory and executable on the processor, the NN interval signal retrieval program configured to implement the steps of:
Acquiring an electrocardiosignal of a subject;
Determining a sinus R wave sequence and a non-sinus R wave sequence corresponding to the electrocardiosignal;
determining sparsity and dispersion of the non-sinus R-wave sequence;
judging whether the non-sinus R wave sequence meets a preset condition according to the sparsity and the dispersion;
When the non-sinus R wave sequence does not meet the preset condition, eliminating target R waves in the sinus R wave sequence according to the non-sinus R wave sequence to obtain NN interval signals;
and when the non-sinus R-wave sequence does not meet the preset condition, rejecting a target R-wave in the sinus R-wave sequence according to the non-sinus R-wave sequence to obtain an NN interval signal, including:
when the non-sinus R wave sequence does not meet the preset condition, determining R waves adjacent to the non-sinus R wave sequence in the sinus R wave sequence;
selecting a preset number of R waves from the adjacent R waves as the target R waves, and eliminating the target R waves;
Dividing the sinus R wave sequence into a plurality of NN analysis fragments by taking the position of the target R wave as a dividing point;
and determining NN interval signals according to the NN analysis fragments.
2. The NN interval signal acquiring apparatus as claimed in claim 1, wherein the NN interval signal acquiring program is configured to implement the steps of:
determining a target fragment with a fragment length smaller than a preset length in the NN analysis fragment;
removing the target fragment from the NN analysis fragment to obtain a removed fragment;
and determining the NN interval signal according to the removed fragments.
3. The NN interval signal acquiring apparatus as claimed in claim 1, wherein the NN interval signal acquiring program is configured to implement the steps of:
the sparsity of the non-sinus R-wave sequence is calculated according to the following formula:
Wherein spark (X) is used to characterize the sparseness of the non-sinus R wave sequence, # (X) is used to characterize the number of non-sinus R waves in the non-sinus R wave sequence, and # (Y) is used to characterize the number of sinus R waves in the sinus R wave sequence.
4. The NN interval signal acquiring apparatus as claimed in claim 1, wherein the NN interval signal acquiring program is configured to implement the steps of:
calculating the dispersion of the non-sinus R-wave sequence according to the following formula:
Wherein Dispersion (X) is used to characterize the Dispersion of the non-sinus R-wave sequence, max (X) is used to characterize the maximum value of R-wave position in the non-sinus R-wave sequence, min (X) is used to characterize the minimum value of R-wave position in the non-sinus R-wave sequence, len (ecgsig) is used to characterize the length of the electrocardiograph signal, cv (X) is used to characterize the coefficient of variation of the non-sinus R-wave sequence.
5. The NN interval signal acquisition apparatus as claimed in any one of claims 1 to 4, wherein the NN interval signal acquisition program is configured to implement the steps of:
preprocessing the electrocardiosignal to obtain a tag sequence;
Inputting the electrocardiosignal and the tag sequence into a preset semantic segmentation prediction model to obtain an output result;
and determining a sinus R wave sequence and a non-sinus R wave sequence corresponding to the electrocardiosignal according to the output result.
6. The NN interval signal acquisition apparatus as claimed in claim 5, wherein the NN interval signal acquisition program is configured to implement the steps of:
determining an RR interval of the electrocardiograph signal;
Determining a heart rate value sequence according to the RR interval;
Determining the size of a window according to the heart rate value sequence, and determining a target interval according to the size of the window;
and marking R waves in the target interval to obtain a tag sequence.
7. The NN interval signal acquisition apparatus as claimed in any one of claims 1 to 4, wherein the NN interval signal acquisition program is configured to implement the steps of:
And when the non-sinus R wave sequence meets the preset condition, performing difference operation on the sinus R wave sequence according to a linear difference value or a cubic spline difference value.
8. An NN interval signal acquisition system, characterized in that the NN interval signal acquisition system comprises: the device comprises an acquisition module, an R wave sequence determination module, a sparsity and dispersion determination module, a judgment module and an NN interval signal determination module;
the acquisition module is used for acquiring electrocardiosignals of the subject;
the R wave sequence determining module is used for determining a sinus R wave sequence and a non-sinus R wave sequence corresponding to the electrocardiosignal;
the sparsity and dispersion determining module is used for determining the sparsity and dispersion of the non-sinus R wave sequence;
the judging module is used for judging whether the non-sinus R wave sequence meets a preset condition according to the sparsity and the dispersion;
the NN interval signal determining module is used for eliminating target R waves in the sinus R wave sequence according to the non-sinus R wave sequence when the non-sinus R wave sequence does not meet the preset condition, so as to obtain NN interval signals;
the NN interval signal determining module is further configured to determine R waves adjacent to the non-sinus R wave sequence in the sinus R wave sequence when the non-sinus R wave sequence does not meet the preset condition;
selecting a preset number of R waves from the adjacent R waves as the target R waves, and eliminating the target R waves;
Dividing the sinus R wave sequence into a plurality of NN analysis fragments by taking the position of the target R wave as a dividing point;
and determining NN interval signals according to the NN analysis fragments.
9. A storage medium, wherein an NN interval signal acquisition program is stored on the storage medium, and when executed by a processor, the NN interval signal acquisition program implements the steps of:
Acquiring an electrocardiosignal of a subject;
Determining a sinus R wave sequence and a non-sinus R wave sequence corresponding to the electrocardiosignal;
determining sparsity and dispersion of the non-sinus R-wave sequence;
judging whether the non-sinus R wave sequence meets a preset condition according to the sparsity and the dispersion;
When the non-sinus R wave sequence does not meet the preset condition, eliminating target R waves in the sinus R wave sequence according to the non-sinus R wave sequence to obtain NN interval signals;
and when the non-sinus R-wave sequence does not meet the preset condition, rejecting a target R-wave in the sinus R-wave sequence according to the non-sinus R-wave sequence to obtain an NN interval signal, including:
when the non-sinus R wave sequence does not meet the preset condition, determining R waves adjacent to the non-sinus R wave sequence in the sinus R wave sequence;
selecting a preset number of R waves from the adjacent R waves as the target R waves, and eliminating the target R waves;
Dividing the sinus R wave sequence into a plurality of NN analysis fragments by taking the position of the target R wave as a dividing point;
and determining NN interval signals according to the NN analysis fragments.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210249257.5A CN114403889B (en) | 2022-03-14 | 2022-03-14 | NN interval signal acquisition device, NN interval signal acquisition system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210249257.5A CN114403889B (en) | 2022-03-14 | 2022-03-14 | NN interval signal acquisition device, NN interval signal acquisition system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114403889A CN114403889A (en) | 2022-04-29 |
| CN114403889B true CN114403889B (en) | 2024-07-05 |
Family
ID=81262699
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210249257.5A Active CN114403889B (en) | 2022-03-14 | 2022-03-14 | NN interval signal acquisition device, NN interval signal acquisition system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114403889B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104127194A (en) * | 2014-07-14 | 2014-11-05 | 华南理工大学 | Depression evaluating system and method based on heart rate variability analytical method |
| CN206792400U (en) * | 2017-01-16 | 2017-12-26 | 吉林东华原医疗设备有限责任公司 | HRV detection means |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016118841A1 (en) * | 2015-01-23 | 2016-07-28 | Medtronic, Inc. | Atrial arrhythmia episode detection in a cardiac medical device |
| CN105902263B (en) * | 2016-04-29 | 2019-04-16 | 深圳市理邦精密仪器股份有限公司 | Assess the method and device of the RR interphase degree of irregularity of electrocardiographic wave |
| CN108491769A (en) * | 2018-03-08 | 2018-09-04 | 四川大学 | Atrial fibrillation sorting technique based on phase between RR and multiple characteristic values |
| CN111110228B (en) * | 2020-01-17 | 2023-04-18 | 武汉中旗生物医疗电子有限公司 | Electrocardiosignal R wave detection method and device |
| CN111803061B (en) * | 2020-06-28 | 2022-12-30 | 武汉中旗生物医疗电子有限公司 | R wave identification method and device based on target detection |
-
2022
- 2022-03-14 CN CN202210249257.5A patent/CN114403889B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104127194A (en) * | 2014-07-14 | 2014-11-05 | 华南理工大学 | Depression evaluating system and method based on heart rate variability analytical method |
| CN206792400U (en) * | 2017-01-16 | 2017-12-26 | 吉林东华原医疗设备有限责任公司 | HRV detection means |
Non-Patent Citations (1)
| Title |
|---|
| Lippman N, Stein KM, Lerman BB. .Comparison of methods for removal of ectopy in measurement of heart rate variability..《Am J Physiol》.1994,H411-8. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114403889A (en) | 2022-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108186011B (en) | Atrial fibrillation detection method, atrial fibrillation detection device and readable storage medium | |
| US11534097B2 (en) | Detection of electrocardiographic signal | |
| CN109171712B (en) | Atrial fibrillation identification method, atrial fibrillation identification device, atrial fibrillation identification equipment and computer readable storage medium | |
| US9042973B2 (en) | Apparatus and method for measuring physiological signal quality | |
| EP2224346B1 (en) | Ecg signal analysis tool | |
| CN110141218B (en) | Electrocardiosignal classification method, electrocardiosignal classification device, program product and storage medium | |
| EP3730049A1 (en) | Apparatus and method for analyzing electrocardiogram | |
| US20200337581A1 (en) | Apparatus and method for analyzing electrocardiogram | |
| CN106923820B (en) | Electrocardiosignal artifact identification method and electrocardiosignal artifact identification device | |
| CN112426160A (en) | Electrocardiosignal type identification method and device | |
| CN113995419B (en) | Atrial fibrillation risk prediction system based on heartbeat rhythm signal and application thereof | |
| CN111832537B (en) | Abnormal electrocardiosignal identification method and abnormal electrocardiosignal identification device | |
| CN116473569A (en) | Electrocardiogram data processing method, system and storage medium | |
| CN111053552A (en) | QRS wave detection method based on deep learning | |
| CN114403889B (en) | NN interval signal acquisition device, NN interval signal acquisition system and storage medium | |
| CN113647959A (en) | Method, device and equipment for identifying waveform of electrocardiographic waveform signal | |
| CN109846473B (en) | Method for detecting single-lead 10-second electrocardiogram noise interference degree | |
| CN115115038B (en) | Model construction method based on single lead electrocardiosignal and gender identification method | |
| CN113288169B (en) | Waveform identification method, device and equipment for electrocardiographic waveform signals | |
| CN111493856B (en) | Correction method and device for heart beat classification, electrocardiogram checking system and storage medium | |
| CN115105084A (en) | Heart beat positioning and classifying method, system, medium and equipment based on deep learning | |
| CN111345815B (en) | Method, device, equipment and storage medium for detecting QRS wave in electrocardiosignal | |
| CN110517783B (en) | Model training method, model training device, heart disease diagnosis apparatus, heart disease diagnosis medium, and heart disease diagnosis program | |
| CN114093521A (en) | Random forest based method and system for estimating blood sugar by reconstructing homogenized samples | |
| CN110477904B (en) | House flapping signal detection method and device |
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 |