CN110448289B

CN110448289B - Heart Rate Variability (HRV) analysis method, device, storage medium and equipment

Info

Publication number: CN110448289B
Application number: CN201910648951.2A
Authority: CN
Inventors: 于小林; 黄橙; 石金之
Original assignee: Shenzhen Biocare Bio Medical Equipment Co ltd
Current assignee: Shenzhen Biocare Bio Medical Equipment Co ltd
Priority date: 2019-07-18
Filing date: 2019-07-18
Publication date: 2022-02-22
Anticipated expiration: 2039-07-18
Also published as: CN110448289A

Abstract

The invention relates to the technical field of medical signal processing, in particular to a Heart Rate Variability (HRV) analysis method, a device, a storage medium and equipment. The method comprises the following steps: acquiring electrocardiogram data; selecting an analysis interval according to the electrocardiogram data to obtain short-range electrocardiogram data; denoising according to the short-range electrocardiogram data to obtain electrocardiogram data to be analyzed; calculating according to the electrocardiogram data to be analyzed to obtain an HRV time domain index, an HRV frequency domain index and an HRV triangular index; acquiring clinical background data of a user corresponding to the electrocardiogram data; calculating according to the HRV time domain index, the HRV frequency domain index and the HRV triangular index to obtain an HRV evaluation integral; calculating according to the clinical background data to obtain a clinical background integral; and calculating according to the HRV evaluation score and the clinical background score to obtain an HRV score. Therefore, the invention has simple operation, high diagnosis accuracy and automatic analysis of the short-range HRV.

Description

Heart Rate Variability (HRV) analysis method, device, storage medium and equipment

Technical Field

The invention relates to the technical field of medical signal processing, in particular to a Heart Rate Variability (HRV) analysis method, a device, a storage medium and equipment.

Background

Heart Rate Variability (HRV) is an index that reflects the function of the heart in pathology, reflecting the heart's ability to control autonomic nerves (sympathetic parasympathetic). Analysis of HRV major clinical applications: assessment of heart failure, sudden cardiac death due to malignant arrhythmia. Clinically there are 3 major forms of HRV: the 24-hour long-range HRV, the short-range HRV and the time-interval HRV are obtained by further analyzing and calculating source data through special software on the basis of dynamic electrocardiogram or static electrocardiogram examination. Aiming at the problems that the HRV normal value is obviously overlapped and crossed between health and patients and the diagnosis is difficult, the method for automatically analyzing the multi-factor short-range HRV is easy and convenient to operate and accurate in diagnosis, and is very important.

Disclosure of Invention

In view of the above, it is necessary to provide a method, an apparatus, a storage medium, and a device for Heart Rate Variability (HRV) analysis.

In a first aspect, the invention provides a method of Heart Rate Variability (HRV) analysis, the method comprising:

acquiring electrocardiogram data;

selecting an analysis interval according to the electrocardiogram data to obtain short-range electrocardiogram data;

denoising according to the short-range electrocardiogram data to obtain electrocardiogram data to be analyzed;

calculating according to the electrocardiogram data to be analyzed to obtain an HRV time domain index, an HRV frequency domain index and an HRV triangular index;

acquiring clinical background data of a user corresponding to the electrocardiogram data;

calculating according to the HRV time domain index, the HRV frequency domain index and the HRV triangular index to obtain an HRV evaluation integral;

calculating according to the clinical background data to obtain a clinical background integral;

and calculating according to the HRV evaluation score and the clinical background score to obtain an HRV score.

In a second aspect, the present invention also provides a heart rate variability analysis device, the device comprising:

the electrocardiogram management module is used for recording electrocardiogram data;

the selection analysis interval module is used for acquiring electrocardiogram data and selecting an analysis interval according to the electrocardiogram data to obtain short-range electrocardiogram data;

the denoising module is used for denoising according to the short-range electrocardiogram data to obtain electrocardiogram data to be analyzed;

a clinical context acquisition module for acquiring clinical context data of a user corresponding to the electrocardiogram data;

the HRV scoring module is used for calculating according to the electrocardiogram data to be analyzed to obtain an HRV time domain index, an HRV frequency domain index and an HRV triangular index, calculating according to the HRV time domain index, the HRV frequency domain index and the HRV triangular index to obtain an HRV evaluation integral, calculating according to the clinical background data to obtain a clinical background integral, and calculating according to the HRV evaluation integral and the clinical background integral to obtain an HRV score.

In a third aspect, the present invention also provides a storage medium storing a computer program of instructions which, when executed by a processor, causes the processor to perform the steps of the method of any one of the first aspect.

In a fourth aspect, the present invention also provides a computer device comprising at least one memory storing a computer program of instructions, at least one processor, the computer program of instructions, when executed by the processor, causing the processor to perform the steps of the method of any one of the first aspect.

In summary, according to the Heart Rate Variability (HRV) analysis method of the present invention, an analysis interval is selected according to the electrocardiogram data to obtain short-range electrocardiogram data; calculating to obtain an HRV time domain index, an HRV frequency domain index and an HRV triangular index after denoising the short-range electrocardiogram data, and calculating to obtain an HRV score according to the HRV time domain index, the HRV frequency domain index, the HRV triangular index and the clinical background data; HRV scores are obtained by combining the HRV indexes with clinical background data, so that the accuracy of the HRV scores is improved, and the diagnosis accuracy is improved; the method is simple and convenient to operate and achieves automatic analysis by selecting an analysis interval, denoising, calculating the HRV index and calculating the HRV score. Therefore, the invention has simple operation, high diagnosis accuracy and automatic analysis of the short-range HRV.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Wherein:

FIG. 1 is a flow diagram of a method for Heart Rate Variability (HRV) analysis in one embodiment;

FIG. 2 is a flow diagram of computing an HRV evaluation integral in one embodiment;

FIG. 3 is a flow diagram of computing an HRV evaluation integral in one embodiment;

FIG. 4 is a flow diagram of calculating a clinical context score according to one embodiment;

FIG. 5 is a flow chart illustrating denoising of ECG data according to an embodiment;

FIG. 6 is a block diagram of a Heart Rate Variability (HRV) analysis device in one embodiment;

FIG. 7 is a block diagram of a computer device in one embodiment.

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.

The Heart Rate Variability (HRV) is the variation of the difference of successive heart cycles, and contains the information of the neurohumoral factors for regulating the cardiovascular system, thereby judging the condition of the cardiovascular system and the like and preventing the cardiovascular system and the like, and possibly being a valuable index for predicting sudden cardiac death and arrhythmic events.

In one embodiment, as illustrated in fig. 1, a Heart Rate Variability (HRV) analysis method is provided that implements the steps of:

s102, acquiring electrocardiogram data;

the electrocardiogram refers to a graph of potential changes in various forms, which are induced from the body surface by an electrocardiograph along with the changes of bioelectricity by the excitation of the heart in each cardiac cycle by a pace-making point, an atrium and a ventricle, and the electrocardiographic measurement technology has been developed to eighteen leads. The examination significance of the electrocardiogram lies in that: it can be used for the examination of arrhythmia, ventricular atrial hypertrophy, myocardial infarction, and myocardial ischemia.

S104, selecting an analysis interval according to the electrocardiogram data to obtain short-range electrocardiogram data;

specifically, one of the leads is selected based on the electrocardiogram data, and a part of the long-duration electrocardiogram data is extracted from the lead as short-range electrocardiogram data.

The short-range electrocardiographic data is electrocardiographic data obtained by cutting off a portion of time duration from one lead of the electrocardiographic chart, and the portion of time duration electrocardiographic data refers to electrocardiographic data obtained by cutting off the portion of time duration from not less than 5 minutes and not more than 4 hours, for example, ii lead, 5 minutes, 10 minutes, 30 minutes, 1 hour, 2 hours, 4 hours, and is not limited in this example.

S106, denoising according to the short-range electrocardiogram data to obtain electrocardiogram data to be analyzed;

specifically, the electrocardiogram data to be analyzed is obtained by removing noise from the short-range electrocardiogram data. Thereby improving the accuracy of the method.

Denoising is to remove waves which are not sent out by electrocardio in the short-range electrocardiogram data, wherein the waves which are not sent out by the electrocardio are interference and artifact caused by noise generated by other reasons, and if the interference and the artifact are not removed, the HRV score can not be accurately calculated.

S108, calculating according to the electrocardiogram data to be analyzed to obtain an HRV time domain index, an HRV frequency domain index and an HRV triangular index;

the HRV temporal index variables include SDNN (unit: ms, standard deviation of all NN intervals), SDANN (unit: ms, average NN interval standard deviation over all 5 minute periods in all recordings), RMSSD (unit: ms, square root of the sum of the squared differences of adjacent NN intervals), SDNN index (unit: ms, average of the standard deviations of NN intervals over all 5 minute periods in all recordings), SDSD (unit: ms, standard deviation of the differences of adjacent NN intervals), NN50 count (unit: ms, log of adjacent NN intervals in all recordings greater than 50ms or log of the following NN interval period), PNN50 (unit:%, NN50 count divided by the total number of NN intervals). The calculation of the HRV time domain index variable may be selected from the prior art, and is not described herein.

And the HRV frequency domain index is obtained by performing Fast Fourier Transform (FFT) on each RR interval change degree value, arranging the processed power spectrum from low to high according to the frequency, defining 0-0.15Hz as low-frequency LF, defining the power of more than 0.15Hz as high-frequency, and calculating to obtain the LF/HF ratio. The calculation of the HRV frequency domain indicator may be selected from the prior art, and will not be described herein.

The HRV triangular index is used for grouping RR intervals from short to long, the inter-group distance is 7.8125ms, RR intervals with the same width are superposed in the same group, and the triangular index is height/low width. The calculation of the HRV triangular index may be selected from the prior art, and will not be described herein.

S110, acquiring clinical background data of a user corresponding to the electrocardiogram data;

the clinical background data includes history of diabetes, chronic heart failure, ventricular hypertrophy, coronary heart disease myocardial infarction, cardiomyopathy, or other organic heart diseases.

S112, calculating according to the HRV time domain index, the HRV frequency domain index and the HRV triangular index to obtain an HRV evaluation integral;

the HRV evaluation integral is calculated according to electrocardiogram data.

S114, calculating according to the clinical background data to obtain a clinical background integral;

and calculating according to the medical history of the clinical background data to obtain a clinical background integral.

The medical history includes a history of diabetes, chronic heart failure, ventricular hypertrophy, coronary heart disease myocardial infarction, cardiomyopathy, or other organic heart diseases.

And S116, calculating according to the HRV evaluation score and the clinical background score to obtain an HRV score.

Specifically, the HRV assessment score is added to the clinical background score to obtain an HRV score.

The HRV score is used to assist in the assessment of heart failure, or in the assessment of sudden cardiac death due to malignant arrhythmia.

According to the method, the HRV score is obtained by combining the HRV index with clinical background data, so that the accuracy of the HRV score is improved, and the diagnosis accuracy is improved; the method is simple and convenient to operate and achieves automatic analysis by selecting an analysis interval, denoising, calculating the HRV index and calculating the HRV score. Therefore, the invention has simple operation, high diagnosis accuracy and automatic analysis of the short-range HRV.

As shown in fig. 2, in an embodiment, the calculating according to the HRV time domain index, the HRV frequency domain index, and the HRV triangular index to obtain an HRV evaluation integral specifically includes:

s202, acquiring actual detection total time corresponding to short-range electrocardiogram data;

the actual detection total time is a time length for the short-range electrocardiogram data selected from the electrocardiogram.

S204, calculating according to the actual total detection time corresponding to the short-range electrocardiogram data to obtain a detection time coefficient;

specifically, let Kt be the detection time coefficient, and ts be the actual total detection time (unit: min)

Kt＝1+(1-ts/(5*288))

S206, calculating according to the HRV time domain index and the detection time coefficient to obtain an HRV time domain index evaluation value;

specifically, an SDNN evaluation value, an SDANN evaluation value, an RMSSD evaluation value, an SDSD evaluation value, an SDNN evaluation value, and a PNN50 evaluation value are calculated according to the HRV time domain index and the detection time coefficient.

Setting the evaluation value as A and the actual measurement value as B, and calculating the evaluation value in the following way:

A＝B*Kt

wherein, when A is the SDNN evaluation value, B is the SDNN actual measurement value; when A is the SDANN evaluation value, B is the SDANN actual measurement value; when A is an RMSSD evaluation value, B is an RMSSD actual measurement value; when A is the SDSD evaluation value, B is the SDSD actual measurement value; when A is an SDNN index evaluation value, B is an SDNN index actual measurement value; when A is the SDANN evaluation value, B is the SDANN actual measurement value;

the PNN50 evaluation equals the PNN50 actual measurement;

s208, calculating according to the HRV frequency domain index to obtain an LF/HF evaluation value;

specifically, Fast Fourier Transform (FFT) is carried out on each RR interval change degree value, processed power spectrums are arranged from low to high according to frequency, 0-0.15Hz is defined as low-frequency LF, power larger than 0.15Hz is defined as high-frequency, an LF/HF ratio is calculated, the LF/HF ratio is an LF/HF actual measurement value, and an LF/HF evaluation value is equal to the LF/HF actual measurement value.

S210, calculating according to the HRV triangular index to obtain a triangular index evaluation value;

specifically, the RR intervals are grouped from short to long, the inter-group distance is 7.8125ms, RR intervals of the same width are superposed in the same group, the actual measured value of the trigonometric index is equal to the height/low width, and the evaluation value of the trigonometric index is equal to the actual measured value of the trigonometric index.

S212, calculating according to the HRV time domain index evaluation value, the LF/HF evaluation value and the triangular index evaluation value to obtain the HRV evaluation integral.

Specifically, the HRV evaluation integral is calculated according to the SDNN evaluation value, the SDANN evaluation value, the RMSSD evaluation value, the SDSD evaluation value, the SDNN index evaluation value, the PNN50 evaluation value, the LF/HF evaluation value, and the triangular index evaluation value.

As shown in fig. 3, in an embodiment, the calculating according to the HRV time domain index evaluation value, the LF/HF evaluation value, and the triangular index evaluation value to obtain the HRV evaluation integral specifically includes:

s302, carrying out abnormity judgment according to the HRV time domain index evaluation value to obtain abnormity classification of the HRV time domain variable;

specifically, when the SDNN evaluation value is greater than 100, the abnormality is classified as normal; when the SDNN evaluation value is greater than or equal to 70 and less than or equal to 100, the abnormity is classified as suspicious; an abnormality is classified as abnormal when the SDNN evaluation value is less than 70;

when the SDANN evaluation value is larger than 100, the abnormity is classified as normal; when the SDANN evaluation value is greater than or equal to 70 and less than or equal to 100, the abnormity is classified as suspicious; an anomaly is classified as abnormal when the SDANN score is less than 70;

an anomaly is classified as normal when the RMSSD evaluation value is greater than 30; when the RMSSD evaluation value is more than or equal to 15 and less than or equal to 30, the abnormality is classified as suspicious; an anomaly is classified as abnormal when the RMSSD evaluation value is less than 15;

an abnormal classification is normal when the SDSD evaluation value is greater than 30; when the SDSD evaluation value is more than or equal to 15 and less than or equal to 30, the abnormity is classified as suspicious; an abnormality is classified as abnormal when the SDSD evaluation value is less than 15;

when the evaluation value of the SDNN index is greater than 80, the abnormity is classified as normal; when the evaluation value of the SDNN index is more than or equal to 50 and less than or equal to 80, the abnormity is classified as suspicious; when the SDNN index evaluation value is less than 50, the abnormality is classified as abnormal;

when the PNN50 evaluation value is more than 8%, the abnormity is classified as normal; when the evaluation value of PNN50 is greater than or equal to 2% and less than or equal to 8%, the abnormity is classified as suspicious; when the evaluation value of PNN50 is less than 2%, classifying the abnormality as abnormal;

s304, carrying out abnormity judgment according to the LF/HF evaluation value to obtain an LF/HF abnormity classification;

specifically, when the LF/HF evaluation value is greater than 4, the abnormity is classified as normal; when the LF/HF evaluation value is more than or equal to 2 and less than or equal to 4, the abnormity is classified as suspicious; when the LF/HF evaluation value is less than 2, the abnormity is classified as abnormal;

s306, carrying out abnormity judgment according to the triangular index evaluation value to obtain an abnormity classification of the HRV triangular index;

specifically, when the triangular index evaluation value is greater than 30, the abnormality is classified as normal; when the evaluation value of the trigonometric index is more than or equal to 15 and less than or equal to 30, the abnormity is classified as suspicious; when the triangular index evaluation value is less than 15, the abnormity is classified as abnormity;

and S308, calculating according to the abnormal classification of the HRV time domain variable, the abnormal classification of the LF/HF and the abnormal classification of the HRV triangular index to obtain the HRV evaluation integral.

Specifically, the abnormal classification of the HRV time domain variable, the abnormal classification of the LF/HF and the abnormal classification of the HRV triangular index are classified and scored, and all the classified scores are added to obtain an HRV evaluation integral. The classification score includes: the score is 0 when the abnormality classification is normal, the score is 0.5 when the abnormality classification is suspicious, and the score is 1 when the abnormality classification is abnormal.

In an embodiment, the calculating according to the clinical context data to obtain a clinical context score specifically includes: and calculating according to the diseased condition in the clinical background data to obtain the clinical background integral. The clinical background data include, but are not limited to, a history of diabetes, chronic heart failure, ventricular hypertrophy (abnormal cardiac hyperconfirmation anatomy), coronary heart disease, myocardial infarction, cardiomyopathy, or other organic heart diseases.

As shown in fig. 4, in an embodiment, the calculating according to the diseased condition in the clinical background data to obtain the clinical background score specifically includes:

s402, performing medical history abnormality judgment according to the diabetes history, chronic heart failure, ventricular hypertrophy, coronary heart disease myocardial infarction, cardiomyopathy or other organic heart diseases in the clinical background data to obtain abnormality classification of the diabetes history, abnormality classification of the chronic heart failure, abnormality classification of the ventricular hypertrophy, abnormality classification of the coronary heart disease myocardial infarction and abnormality classification of the cardiomyopathy or other organic heart diseases;

specifically, the abnormal classification of the medical history includes: presence, absence and unclear background.

S404, calculating according to the abnormal classification of the diabetes history, the abnormal classification of the chronic heart failure, the abnormal classification of the ventricular hypertrophy, the abnormal classification of the myocardial infarction of the coronary heart disease and the abnormal classification of the cardiomyopathy or other organic heart diseases to obtain the clinical background integral.

Specifically, a medical history classification score is made according to the abnormality classification of the diabetes history, the abnormality classification of chronic heart failure, the abnormality classification of ventricular hypertrophy, the abnormality classification of coronary heart disease myocardial infarction, the abnormality classification of cardiomyopathy or other organic heart diseases, and all the classification scores are added to obtain a clinical background score. The medical history classification score includes: score 1 if any, score 0 if no, and score 0.5 if background is unknown.

In one embodiment, the short-range electrocardiogram data refers to data selected from the II leads of a 12-lead electrocardiogram for a preset time. In the 12-lead electrocardiogram, the base line of the II lead is stable, the R/T ratio is larger than that of other leads, and the selection of the II lead is favorable for improving the accuracy of the method.

In one embodiment, the selecting an analysis interval according to the electrocardiogram data to obtain short-range electrocardiogram data specifically includes: acquiring an analysis duration parameter; and selecting a stable baseline and a large R/T ratio range as short-range electrocardiogram data according to the analysis duration parameter and the electrocardiogram data, wherein the short-range electrocardiogram data is used as an analysis basis of a heart rate variability analysis method.

The analysis duration parameter is a time length of data captured from the electrocardiogram, and the analysis duration parameter is not less than 5 minutes and not more than 4 hours, such as 5 minutes, 10 minutes, 30 minutes, 1 hour, 2 hours, and 4 hours, which is not limited by the example.

The R/T ratio is large, namely the height of the T wave relative to the baseline is less than 30% of the height of the R wave relative to the baseline.

The R wave refers to a normal waveform on an electrocardiogram.

The T wave is an electric wave with lower amplitude and longer wave width after QRS wave complex, and reflects the repolarization process after ventricular excitation. The order of repolarization of the ventricles is reversed with respect to the depolarization process, which proceeds slowly from the outer layer to the inner layer, with the negative potential of the depolarized portion of the outer layer returning first to the positive potential at rest, making the outer layer positive and the inner layer negative, and thus in substantially the same direction as the vector at depolarization.

As shown in fig. 5, in an embodiment, the denoising according to the short-range electrocardiogram data to obtain electrocardiogram data to be analyzed specifically includes:

s502, eliminating interference, artifact and non-sinus ventricular download heartbeat data according to the short-range electrocardiogram data to obtain short-range electrocardiogram data to be labeled;

the interference and the artifact are not waves emitted by the electrocardio, but noise generated by other reasons, such as interference generated by abnormal noise in the environment. The artifact refers to electrocardiogram electrostatic interference caused by the reason of the instrument. The method for identifying interference and artifacts can be selected from the prior art and will not be described herein.

Non-sinus ventricular-derived heart diseases such as ectopic heart beat, abnormal heart rhythm or ectopic beat are common heart diseases, and the identification method can be selected from the prior art and is not described herein.

S504, identifying and labeling are carried out according to the short-range electrocardiogram data to be labeled to obtain the heartbeat attribute of the short-range electrocardiogram data;

specifically, sinus beats are labeled N, supraventricular ectopic beats are labeled S, ventricular ectopic beats are labeled V, pacing beats are labeled P, atrial fibrillation beats are labeled Af, and atrial flutter beats are labeled Af. The method for labeling the heart beat attribute can be selected from the prior art, and is not described herein.

S506, obtaining a cardiac interval according to the cardiac attribute of the short-range electrocardiogram data;

specifically, two adjacent cardiac attributes on the electrocardiogram are combined into a cardiac interval, such as an N-N interval (also called NN interval), an N-V interval (also called NV interval), a V-V interval (also called VV interval), and an N-S interval (also called NS interval).

And S508, obtaining electrocardiogram data to be analyzed according to the cardiac interval.

Specifically, the N-N interval is effective heart beat, and the result of dividing the analyzed heart beat number by the total heart beat number in the analysis interval is more than or equal to 0.7, so that the data of the N-N interval is used as electrocardiogram data to be analyzed; if the result of dividing the analysis heart beat number by the total heart beat number of the analysis interval is less than 0.7, abandoning the analysis of the short-range electrocardiogram data; other cardiac intervals are ineffective heartbeats and this portion of electrocardiographic data is not analyzed, e.g., N-V intervals, V-V intervals, N-S intervals. Therefore, the electrocardiogram data to be analyzed obtained after denoising is effective heartbeat.

The analyzed heart beat number refers to the total number of heartbeats of all N-N intervals in the short-range electrocardiogram data.

The total heart beat number of the analysis interval refers to the total heart beat number of the short-range electrocardiogram data.

In one embodiment, after the calculating according to the HRV evaluation score and the clinical background score to obtain an HRV score, the method further comprises: when the clinical background score is less than or equal to 0.5, the disease diagnosis result is that the HRV detection is not abnormal; when the HRV evaluation score is less than or equal to 0.5, the disease diagnosis result is that the HRV detection is not abnormal; when the clinical background score is greater than 0.5, the HRV evaluation score is greater than 0.5, and the HRV score is greater than or equal to 3, the disease diagnosis result is HRV abnormity; when the clinical background score is more than 0.5, the HRV evaluation score is more than 0.5, and the HRV score is more than 1 and less than 3, the disease diagnosis result is the HRV suspicious abnormality; and when the clinical background score is more than 0.5, the HRV evaluation score is more than 0.5 and the HRV score is less than or equal to 1, the disease diagnosis result is no abnormality.

As illustrated in fig. 6, in one embodiment, there is provided a heart rate variability analysis device, the device comprising:

an electrocardiogram management module 601, configured to record electrocardiogram data;

a section selection and analysis module 603, configured to obtain electrocardiogram data, and select an analysis section according to the electrocardiogram data to obtain short-range electrocardiogram data;

a denoising module 604, configured to perform denoising according to the short-range electrocardiogram data to obtain electrocardiogram data to be analyzed;

a clinical context acquiring module 602, configured to acquire clinical context data of a user corresponding to the electrocardiogram data;

the HRV scoring module 605 is configured to calculate according to the electrocardiogram data to be analyzed to obtain an HRV time domain index, an HRV frequency domain index, and an HRV triangular index, calculate according to the HRV time domain index, the HRV frequency domain index, and the HRV triangular index to obtain an HRV evaluation integral, calculate according to the clinical background data to obtain a clinical background integral, and calculate according to the HRV evaluation integral and the clinical background integral to obtain an HRV score.

The device obtains the HRV score by combining the HRV index with clinical background data, so that the HRV score accuracy is improved, and the diagnosis accuracy is improved; the method is simple and convenient to operate and achieves automatic analysis by selecting an analysis interval, denoising, calculating the HRV index and calculating the HRV score. Therefore, the invention has simple operation, high diagnosis accuracy and automatic analysis of the short-range HRV.

FIG. 7 is a diagram illustrating an internal structure of a computer device in one embodiment. The computer device may specifically be a server and a terminal device, where the server includes but is not limited to a high-performance computer and a high-performance computer cluster; the terminal devices include, but are not limited to, mobile terminal devices including, but not limited to, mobile phones, tablet computers, smart watches, and laptops, and desktop terminal devices including, but not limited to, desktop computers and in-vehicle computers. As shown in fig. 7, the computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program that, when executed by the processor, causes the processor to implement a method of Heart Rate Variability (HRV) analysis. The internal memory may also have stored therein a computer program that, when executed by the processor, causes the processor to perform a method of Heart Rate Variability (HRV) analysis. Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a method of Heart Rate Variability (HRV) analysis provided herein may be implemented in the form of a computer program that is executable on a computer device such as that shown in fig. 7. The memory of the computer device may store therein individual program templates constituting a Heart Rate Variability (HRV) analysis device. For example, the electrocardiogram management module 601, the analysis interval selection module 603, the denoising module 604, the clinical background acquisition module 602, and the HRV scoring module 605 are selected.

In one embodiment, the present invention also provides a storage medium storing a computer program of instructions that, when executed by a processor, cause the processor to perform the steps of:

acquiring electrocardiogram data;

and calculating according to the HRV time domain index, the HRV frequency domain index, the HRV triangular index and the clinical background data to obtain an HRV score.

In one embodiment, the present invention also provides a computer device comprising at least one memory, at least one processor, the memory storing a computer program of instructions which, when executed by the processor, causes the processor to perform the steps of:

acquiring electrocardiogram data;

It should be noted that the Heart Rate Variability (HRV) analysis method, the Heart Rate Variability (HRV) analysis apparatus, the computer device and the computer readable storage medium described above belong to one general inventive concept, and the contents of the embodiments of the Heart Rate Variability (HRV) analysis method, the Heart Rate Variability (HRV) analysis apparatus, the computer device and the computer readable storage medium are mutually applicable.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A method of Heart Rate Variability (HRV) analysis, the method comprising:

acquiring electrocardiogram data;

calculating according to the HRV evaluation score and the clinical background score to obtain an HRV score;

wherein, the calculating according to the clinical background data to obtain the clinical background integral specifically comprises:

performing history abnormality judgment according to the diabetes history, chronic heart failure, ventricular hypertrophy, coronary heart disease myocardial infarction, cardiomyopathy or other organic heart diseases in the clinical background data to obtain abnormality classification of the diabetes history, abnormality classification of the chronic heart failure, abnormality classification of the ventricular hypertrophy, abnormality classification of the coronary heart disease myocardial infarction and abnormality classification of the cardiomyopathy or other organic heart diseases;

and calculating according to the abnormal classification of the diabetes history, the abnormal classification of the chronic heart failure, the abnormal classification of the ventricular hypertrophy, the abnormal classification of the coronary heart disease myocardial infarction and the abnormal classification of the cardiomyopathy or other organic heart diseases to obtain the clinical background integral.

2. The method as claimed in claim 1, wherein the calculating according to the HRV time domain index, the HRV frequency domain index, and the HRV triangular index to obtain an HRV evaluation integral specifically includes:

acquiring actual detection total time corresponding to the short-range electrocardiogram data;

calculating according to the actual detection total time corresponding to the short-range electrocardiogram data to obtain a detection time coefficient;

calculating according to the HRV time domain index and the detection time coefficient to obtain an HRV time domain index evaluation value;

calculating according to the HRV frequency domain index to obtain an LF/HF evaluation value, wherein the LF is a low frequency of 0-0.15HZ, the HF is a high frequency greater than 0.15HZ, and the LF/HF evaluation value is a ratio of the LF to the HF;

calculating according to the HRV triangular index to obtain a triangular index evaluation value;

and calculating according to the HRV time domain index evaluation value, the LF/HF evaluation value and the triangular index evaluation value to obtain the HRV evaluation integral.

3. The method as claimed in claim 2, wherein the calculating according to the HRV time domain index evaluation value, the LF/HF evaluation value, and the triangular index evaluation value to obtain the HRV evaluation integral specifically includes:

performing abnormity judgment according to the HRV time domain index evaluation value to obtain abnormity classification of the HRV time domain variable;

carrying out abnormity judgment according to the LF/HF evaluation value to obtain an LF/HF abnormity classification;

carrying out abnormity judgment according to the triangular index evaluation value to obtain an abnormity classification of the HRV triangular index;

and calculating according to the abnormal classification of the HRV time domain variable, the abnormal classification of the LF/HF and the abnormal classification of the HRV triangular index to obtain the HRV evaluation integral.

4. The method according to any one of claims 1 to 3, wherein selecting an analysis interval from the electrocardiogram data to obtain short-range electrocardiogram data comprises:

acquiring an analysis duration parameter;

and selecting a stable baseline and a large R/T ratio range as short-range electrocardiogram data according to the analysis duration parameter and the electrocardiogram data, wherein the short-range electrocardiogram data is used as an analysis basis of a heart rate variability analysis method, and the large R/T ratio means that the height of the T wave relative to the baseline is less than 30% of the height of the R wave relative to the baseline.

5. The method according to any one of claims 1 to 3, wherein the denoising according to the short-range electrocardiogram data to obtain the electrocardiogram data to be analyzed specifically comprises:

eliminating interference, artifact and non-sinus ventricular downlink heartbeat data according to the short-range electrocardiogram data to obtain short-range electrocardiogram data to be labeled;

performing identification and labeling according to the short-range electrocardiogram data to be labeled to obtain the heartbeat attribute of the short-range electrocardiogram data;

obtaining the heart beat interval according to the heart beat attribute of the short-range electrocardiogram data;

and obtaining electrocardiogram data to be analyzed according to the cardiac intervals.

6. A heart rate variability analysis device, characterized in that the device comprises:

the HRV scoring module is used for calculating according to the electrocardiogram data to be analyzed to obtain an HRV time domain index, an HRV frequency domain index and an HRV triangular index, calculating according to the HRV time domain index, the HRV frequency domain index and the HRV triangular index to obtain an HRV evaluation integral, calculating according to the clinical background data to obtain a clinical background integral, and calculating according to the HRV evaluation integral and the clinical background integral to obtain an HRV score; the HRV scoring module is specifically configured to perform medical history abnormality judgment according to the diabetes history, chronic heart failure, ventricular hypertrophy, coronary heart disease myocardial infarction, cardiomyopathy or other organic heart diseases in the clinical background data to obtain an abnormality classification of the diabetes history, an abnormality classification of the chronic heart failure, an abnormality classification of the ventricular hypertrophy, an abnormality classification of the coronary heart disease myocardial infarction, and an abnormality classification of the cardiomyopathy or other organic heart diseases; and calculating according to the abnormal classification of the diabetes history, the abnormal classification of the chronic heart failure, the abnormal classification of the ventricular hypertrophy, the abnormal classification of the coronary heart disease myocardial infarction and the abnormal classification of the cardiomyopathy or other organic heart diseases to obtain the clinical background integral.

7. A storage medium storing a computer program of instructions which, when executed by a processor, causes the processor to carry out the steps of the method according to any one of claims 1 to 5.

8. A computer device comprising at least one memory storing a program of computer instructions which, when executed by the processor, causes the processor to perform the steps of the method of any one of claims 1 to 5, at least one processor.