KR20210015306A - Apparatuses and methods for classifying heart condition based on class probability output network - Google Patents

Abstract

The present invention relates to a method and an apparatus for classifying a heart state based on a class probability output network. The method for classifying a heart state according to an embodiment of the present invention comprises the steps of: estimating a parameter of a gamma distribution representing a statistical characteristic of an interval between electrocardiogram signals; calculating the distance between the center point of the estimated parameter of the gamma distribution and that of a pre-learned parameter of the gamma distribution; inputting the calculated distance between the center points to a class probability output network to determine a significance probability of a normal class and an abnormal class; and classifying the collected electrocardiogram signal into a normal wave or an abnormal wave by comparing the significance probability of the determined normal class with that of the abnormal class. The method for classifying a heart state according to an embodiment of the present invention includes a step of, if the electrocardiogram signal is classified into the normal wave, additionally collecting the interval of the normal electrocardiogram signal to calculate a correlation coefficient between a current interval and a next interval, and determining the heart state as a normal state or an abnormal state using the calculated correlation coefficient value. The present invention can diagnose a pre-symptom of a heart abnormality in advance.

Description

A method and apparatus for classifying heart conditions based on class probability output network {APPARATUSES AND METHODS FOR CLASSIFYING HEART CONDITION BASED ON CLASS PROBABILITY OUTPUT NETWORK}

The present invention relates to a method and apparatus for classifying heart conditions based on a class probability output network.

The electrocardiogram (ECG) signal is an important signal used to determine diseases of the heart system.By measuring the electrical signal generated by the heart, it can determine the presence or absence of a disease by checking the presence or absence of the conduction system from the heart to the electrode. It's a signal to be there.

The heartbeat, which is the cause of the ECG signal, is the impulse that originates from the sinus node located in the right atrium. Activates the posterior ventricle. The septum is the fastest and the thin-walled right ventricle is activated before the thick-walled left ventricle. The depolarization wave transmitted to Purkinje Fiber causes ventricular contraction as it spreads from the endocardium to the outer pericardium like a wavefront from the myocardium. Because electrical impulses are normally conducted through the heart, the heart contracts about 60-100 times per minute. Each contraction is expressed as one heart rate.

The normal ECG signal is composed of PQRST wave, P wave indicates atrial depolarization and contraction, QRS indicates ventricular depolarization and contraction, and T wave indicates ventricular depolarization. Doctors can infer the heart condition from the pattern of the PQRST wave. These waves must have a standard shape in order for the heart to have normal electrical activity. In order to grasp the normal state of the heart, it is necessary to determine whether features such as the duration of each wave, the interval between each wave, the amplitude of each wave, and kurtosis fall within the normal range.

On the other hand, determination of the presence or absence of abnormal heart health using features used in the conventional heart rate variability (HRV) analysis takes a long time and does not provide a probability-based determination measure.

In addition, in the conventional technology for determining the presence or absence of abnormal heart health, it is difficult to grasp the potential risk of the heart when the heart pulse is normal.

Embodiments of the present invention provide a statistical-based feature that is efficient for heart health and, based on this, provide a probabilistic measure for the presence or absence of heart health, thereby providing more reliable diagnostic information. It is intended to provide a state classification method and apparatus.

According to an embodiment of the present invention, there is provided a method for classifying a heart state performed by an apparatus for classifying a heart state, the method comprising: estimating a parameter of a gamma distribution indicating a statistical characteristic of an interval of an ECG signal; Calculating a distance between the estimated parameter of the gamma distribution and a center point of the parameter of the previously learned gamma distribution; Determining a significance probability of a normal class and an abnormal class by inputting the calculated distance between the center points into a class probability output network; And classifying the ECG signal as a normal wave or an abnormal wave by comparing the determined significance probabilities of the normal class and the abnormal class with each other, and a class probability output network-based cardiac state classification method may be provided.

The interval of the ECG signal may be an R-R interval of the ECG signal or a beat-to-beat interval.

In calculating the distance between the center points, the distance between the estimated parameter of the gamma distribution and the center point of the parameter of the previously learned gamma distribution may be calculated on a log scale.

The calculated distance between the center points may be output by a kernel function and input to a class probability output network.

The determining of the significance probability includes allocating a Gaussian kernel function to the distance between the calculated center points and determining a weight value according to the allocated Gaussian kernel function to determine a normal class and an abnormal class for classifying a heart state. You can calculate a function.

In determining the significance probability, the calculated distribution of the decision function for the normal class and the abnormal class may be estimated as a parameter of the beta distribution.

In determining the significance probability, the significance probability for hypotheses for the normal class and the abnormal class may be determined using a beta cumulative distribution function in which the parameter of the estimated beta distribution is reflected.

In the above method, when the ECG signal is classified as a normal wave, an interval of the normal ECG signal is additionally collected to calculate a correlation coefficient between the current interval and the next interval, and the heart condition is normalized using the calculated correlation coefficient value. It may further include determining a state or an abnormal state.

In determining the heart state as a normal state or an abnormal state, the calculated correlation coefficient value is applied to a pre-learned beta distribution to calculate a significance probability for a normal state through a class probability output network, and the calculated significance probability The heart state may be determined as a normal state or an abnormal state by using.

In determining the heart state as a normal state or an abnormal state, if the calculated significance probability is greater than or equal to a threshold value, the heart state may be determined as a normal state.

On the other hand, according to another embodiment of the present invention, a memory for storing at least one program; And a processor connected to the memory, wherein the processor estimates a parameter of a gamma distribution indicating a statistical characteristic of an interval of an electrocardiogram signal by executing the at least one program, and Calculate the distance between the center points of the parameters of the learned gamma distribution, input the calculated distance between the center points to the class probability output network to determine the significance probability of the normal class and the abnormal class, and determine the significance probability of the determined normal class and the abnormal class. Electrocardiogram waves can be classified as either normal or abnormal waves by comparing the significance probabilities.

The interval of the ECG signal may be an R-R interval of the ECG signal or a beat-to-beat interval.

The processor may calculate a distance between the estimated parameter of the gamma distribution and a center point of the parameter of the previously learned gamma distribution on a log scale.

The calculated distance between the center points may be output by a kernel function and input to a class probability output network.

The processor may allocate a Gaussian kernel function to the calculated distance between the center points, determine a weight value according to the allocated Gaussian kernel function, and calculate a determination function for a normal class and an abnormal class for classifying a heart state. have.

The processor may estimate the calculated distribution of the decision function for the normal class and the abnormal class as a parameter of the beta distribution.

The processor may determine a significance probability for hypotheses for the normal class and the abnormal class using a beta cumulative distribution function in which the parameter of the estimated beta distribution is reflected.

When the ECG signal is classified as a normal wave, the processor calculates a correlation coefficient between the current interval and the next interval by additionally collecting the interval of the normal ECG signal, and normalizes the heart condition using the calculated correlation coefficient value. It can be determined as a state or abnormal state.

The processor calculates a significance probability for a steady state through a class probability output network by applying the calculated correlation coefficient value to a pre-learned beta distribution, and determines the heart state as a normal state or an abnormal state using the calculated significance probability. Can be determined by the state.

The processor may determine the heart state as a normal state when the calculated significance probability is greater than or equal to a threshold value.

Meanwhile, according to another embodiment of the present invention, as a non-transitory computer-readable storage medium including at least one program executable by a processor, when the at least one program is executed by the processor, the processor causes: Estimate a parameter of a gamma distribution representing a statistical characteristic of an ECG signal interval, calculate a distance between the estimated parameter of the gamma distribution and a center point of the parameter of the previously learned gamma distribution, and calculate the distance between the calculated center point Including instructions for inputting to a class probability output network to determine the significance probability of the normal class and the abnormal class, and comparing the determined significance probability of the normal class and the abnormal class with each other to classify the ECG wave as a normal wave or an abnormal wave, A non-transitory computer-readable storage medium may be provided.

Embodiments of the present invention may provide information on the presence or absence of health of the heart with a small number of parameters by using the interval information of the heart rate in heart health diagnosis.

Embodiments of the present invention may provide information on the presence or absence of abnormal heart health in real time in an environment in which a portable heart rate detector is provided.

Embodiments of the present invention may provide a measure of the potential risk of the heart even when the heart's pulse is normal. That is, since the embodiments of the present invention are already late when an abnormality in the heartbeat pattern is found, even when the heartbeat pattern is found to be normal, how much is normal and a precursor symptom of a heart abnormality can be diagnosed in advance.

1 is a block diagram illustrating a configuration of an apparatus for classifying a heart state based on a class probability output network and a heart rate detector according to an embodiment of the present invention.
2 is a flowchart illustrating a method for classifying a heart state based on a class probability output network according to an embodiment of the present invention.
3 is a flowchart illustrating a classification operation of a normal wave and an abnormal wave in a method for classifying a heart state based on a class probability output network according to an embodiment of the present invention.
4 is a flowchart illustrating a classification operation of a normal state and an abnormal state in a method for classifying a heart state based on a class probability output network according to an embodiment of the present invention.
5 is a diagram showing the presence or absence of an abnormality in an ECG waveform according to a parameter of a gamma distribution of a log scale in an embodiment of the present invention.
6 and 7 are diagrams illustrating the presence or absence of an abnormality in an ECG waveform according to an SDNN feature and an RMSSD feature in a method according to an embodiment of the present invention.
8 is a view showing an LDA output histogram and beta variable estimation according to a class of an ECG waveform used in an embodiment of the present invention.
9 to 12 are diagrams showing simultaneous occurrence of current and next RR intervals according to the presence or absence of a heart abnormality according to an embodiment of the present invention.
13 is a diagram illustrating a distribution of a correlation coefficient between a current and a next RR interval according to the presence or absence of a heart abnormality according to an embodiment of the present invention.
14 is a diagram illustrating a distribution of a significance probability (p-value) according to a class of a cardiac abnormality according to an embodiment of the present invention.

Since the present invention can make various changes and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail.

However, this is not intended to limit the present invention to a specific embodiment, it is to be understood to include all changes, equivalents, or substitutes included in the spirit and scope of the present invention.

Terms such as first and second may be used to describe various components, but the components should not be limited by the terms. These terms are used only for the purpose of distinguishing one component from another component. For example, without departing from the scope of the present invention, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. The term and/or includes a combination of a plurality of related listed items or any of a plurality of related listed items.

When a component is referred to as being "connected" or "connected" to another component, it is understood that it may be directly connected or connected to the other component, but other components may exist in the middle. Should be. On the other hand, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there is no other component in the middle.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In the present application, terms such as "comprise" or "have" are intended to designate the presence of features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, but one or more other features. It is to be understood that the presence or addition of elements or numbers, steps, actions, components, parts, or combinations thereof, does not preclude in advance.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs. Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and should not be interpreted as an ideal or excessively formal meaning unless explicitly defined in this application. Does not.

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the accompanying drawings. In describing the present invention, in order to facilitate an overall understanding, the same reference numerals are used for the same elements in the drawings, and duplicate descriptions for the same elements are omitted.

1 is a block diagram illustrating a configuration of an apparatus for classifying a heart state based on a class probability output network and a heart rate detector according to an embodiment of the present invention.

As shown in FIG. 1, the apparatus 100 for classifying a heart state based on a class probability output network according to an embodiment of the present invention is connected to the heart rate detector 101. The apparatus 100 for classifying a heart condition based on a class probability output network according to an embodiment of the present invention includes a receiving module 110, a memory 120, and a processor 130. However, not all of the illustrated components are essential components. The heart state classification apparatus 100 may be implemented by more components than the illustrated components, and the heart state classification apparatus 100 may be implemented by fewer components than the illustrated components.

First, the heart rate detector 101 may measure a heart rate and measure an electrocardiogram (ECG) signal. For example, the heart rate detector 101 may be implemented as a portable heart rate detector. The electrocardiogram (ECG) signal may include information about an R-R interval of the heart or a beat-to-beat interval.

The apparatus 100 for classifying a heart condition according to an embodiment of the present invention diagnoses the presence or absence of an abnormality in heart health using information on the R-R interval of the heart or the beat-to-beat interval of the heart.

The heart state classification apparatus 100 according to an embodiment of the present invention performs a class probability output network (CPON) based heart state classification operation for classifying a heart state from an electrocardiogram (ECG) signal. To this end, the heart condition classification apparatus 100 analyzes the R-R interval of the ECG signal as a gamma distribution parameter and classifies it as a normal (NR) or abnormal (AN) ECG wave. In addition, in the case of a normal ECG wave, the heart state classification apparatus 100 finally determines whether the heart is in a normal state based on a correlation between the continuous R-R interval and long-term analysis of the ECG. In an embodiment of the present invention, a heart state may be classified through a hypothesis test model for a heart state using a class probability output network (CPON), which is a conditional class probability.

Specifically, the heart condition classification apparatus 100 extracts a statistical feature from the heart rate interval information provided by the heart rate detector 101 as a parameter of a gamma distribution. In addition, the apparatus 100 for classifying a heart state may provide a p-value of hypothesis verification for two states by using a probability-based classifier for the normal and abnormal waves of the heart.

In addition, the heart condition classification apparatus 100 calculates a correlation coefficient between RR intervals to estimate the potential risk of the heart when the heart wave is normal, and uses a probability-based hypothesis verification model to determine the potential of the heart. You can provide a measure of risk.

Hereinafter, a detailed configuration and operation of each component of the heart condition classification apparatus 100 of FIG. 1 will be described.

The receiving module 110 receives an electrocardiogram signal, which is heart rate information detected by the heart rate detector 101.

The memory 120 stores at least one program.

The processor 130 is connected to the receiving module 110 and the memory 120. By executing the at least one program, the processor 130 estimates a parameter of a gamma distribution representing a statistical characteristic of an interval of an ECG signal, and a center point of the parameter of the estimated gamma distribution and a parameter of the previously learned gamma distribution. Calculate the distance between the distances, and input the calculated distance between the center points into the class probability output network to determine the significance probability of the normal class and the abnormal class, and compare the determined significance probability of the normal class and the abnormal class to ECG wave Is classified as a standing wave or an abnormal wave.

According to embodiments, the interval of the collected ECG signals may be an R-R interval of the collected ECG signals or a beat-to-beat interval.

According to embodiments, the processor 130 may calculate a distance between the estimated parameter of the gamma distribution and the center point of the parameter of the previously learned gamma distribution on a log scale.

According to embodiments, the calculated distance between center points may be output by a kernel function and input to a class probability output network.

According to embodiments, the processor 130 allocates a Gaussian kernel function to the calculated distance between the center points, determines a weight value according to the assigned Gaussian kernel function, and determines a normal class and an abnormal class for classification of a heart state. You can calculate the decision function.

According to embodiments, the processor 130 may estimate the calculated distribution of the decision function for the normal class and the abnormal class as a parameter of the beta distribution.

According to embodiments, the processor 130 may determine the significance probability of hypotheses for the normal class and the abnormal class by using the beta cumulative distribution function in which the parameter of the estimated beta distribution is reflected.

According to embodiments, when the collected ECG signal is classified as a normal wave, the processor 130 additionally collects the interval of the normal ECG signal to calculate a correlation coefficient between the current interval and the next interval, and the calculated correlation coefficient The value can be used to determine the heart condition as normal or abnormal.

According to embodiments, the processor 130 applies the calculated correlation coefficient value to a pre-learned beta distribution to calculate a significance probability for a steady state through a class probability output network, and uses the calculated significance probability to calculate the The state can be determined as a normal state or an abnormal state.

According to embodiments, the processor 130 may determine the heart state as a normal state when the calculated significance probability is greater than or equal to a threshold value.

2 is a flowchart illustrating a method for classifying a heart state based on a class probability output network according to an embodiment of the present invention.

In this problem of classifying the heart condition, the R-R interval detected from the ECG signal data is collected on a window of a finite size and used to obtain statistically meaningful data distribution information and to determine the heart condition. The process of classifying heart conditions is repeated every sampling time. Here, if the ECG wave of cardiac activity is completely normal, it is determined as normal (NR, Normal), otherwise it is considered as abnormal (AN, Abnormal).

The overall process of a method for classifying a heart condition according to an embodiment of the present invention is shown in FIG. 2. Here, the automatic classification process of the heart condition is as follows.

In step S101, the heart condition classification apparatus 100 detects the R-R interval from the ECG signal data. The detected R-R interval is collected within a window of a fixed size (eg, 30 seconds) every sampling time (eg, 10 seconds).

In step S102, the heart condition classification apparatus 100 estimates a parameter of the gamma distribution from the distribution of the R-R interval in the window.

In steps S103 and S104, the cardiac state classification apparatus 100 calculates the distance between the parameter of the gamma distribution estimated for the ECG wave of the NR and AN classes and the center value of the parameter of the previously learned gamma distribution on a log scale. And analyze the distance to the center point of NR or AN.

In step S105, the heart condition classification apparatus 100 outputs a given distance by a kernel function. The calculated distance is transferred to an input of a class probability output network (CPON).

In steps S106 and S107, the heart condition classification apparatus 100 determines p-value values for testing the hypotheses of the NR and AN classes.

In step S108, the heart condition classification apparatus 100 determines a normal or abnormal wave for the ECG pattern by comparing the p-value values of the NR and AN classes. If the significance probability of the NR class is greater than or equal to the significance probability of the AR class, the cardiac state classification apparatus 100 determines a normal wave.

On the other hand, in step S109, if the significance probability of the NR class is not greater than the significance probability of the AR class, the cardiac state classification apparatus 100 determines an abnormal wave.

Here, if the R-R interval is classified as an NR class representing a normal ECG wave, the following procedure is applied to determine whether the heart is in a normal state as follows.

In step S110, the heart condition classification apparatus 100 collects a normal R-R interval for a fixed time window (eg, a 30 minute window).

In step S111, the heart condition classification apparatus 100 calculates a correlation coefficient between the current R-R interval and the next R-R interval.

In step S112, the apparatus 100 for classifying a heart state applies a correlation coefficient value to the previously learned beta distribution to obtain a significance probability value for a normal heart state through a class probability output network CPON.

The heart state classification apparatus 100 then determines whether or not the final heart state is abnormal using a significance probability value. In step S113, the heart condition classification apparatus 100 checks whether the significance probability value is equal to or greater than a preset threshold value δ.

In step S114, if the significance probability value is greater than or equal to a preset threshold value δ, the heart state classification apparatus 100 accepts the hypothesis for a normal heart state. Here, as an example, the routine threshold is given as 0.05.

On the other hand, in step S114, if the significance probability value is less than the preset threshold value δ, the cardiac state classification apparatus 100 classifies it as an abnormal heart state.

An embodiment of the present invention provides accurate estimation of conditional class probabilities because, in learning of the classifier, not only the kernel parameters but also the beta distribution parameters are adjusted so that the output distribution of the classifier is closer to the ideal beta distribution. In addition, the class probability output network CPON according to an embodiment of the present invention may provide an uncertainty measure for a final decision of classification by estimating a confidence interval for a conditional class probability.

3 is a flowchart illustrating a classification operation of a normal wave and an abnormal wave in a method for classifying a heart state based on a class probability output network according to an embodiment of the present invention.

In step S201, the apparatus 100 for classifying a heart condition estimates a parameter of a gamma distribution indicating a statistical characteristic of an interval of an ECG signal.

In step S202, the heart condition classification apparatus 100 calculates a distance between the estimated parameter of the gamma distribution and the center point of the parameter of the previously learned gamma distribution.

In step S203, the heart condition classification apparatus 100 determines the significance probability of the normal class and the abnormal class by inputting the calculated distance between the center points to the class probability output network.

In step S204, the cardiac state classification apparatus 100 compares the determined significance probability of the normal class and the abnormal class with each other, and classifies the collected ECG signal as a normal wave or an abnormal wave.

4 is a flowchart illustrating a classification operation of a normal state and an abnormal state in a method for classifying a heart state based on a class probability output network according to an embodiment of the present invention.

It is performed when the normal wave and the abnormal wave are classified as a normal wave in the classification operation of FIG. 3.

In step S301, the heart condition classification apparatus 100 classifies the collected ECG signal as a normal wave.

In step S302, the heart condition classification apparatus 100 additionally collects the interval of the normal ECG signal.

In step S303, the heart condition classification apparatus 100 calculates a correlation coefficient between the current interval and the next interval.

In step S304, the heart state classification apparatus 100 determines the heart state as a normal state or an abnormal state by using the correlation coefficient value.

Meanwhile, in an embodiment of the present invention, a feature extraction operation using an interval of a heartbeat will be described in detail.

5 is a diagram showing the presence or absence of an abnormality in an ECG waveform according to a parameter of a gamma distribution of a log scale in an embodiment of the present invention.

)에 의하여 분석된다. 여기서, (

)는 각 각 감마 분포의 모양과 스케일을 결정한다. 이러한 분석은 2 개의 임의의 이벤트 사이의 간격이 감마 분포의 적절한 파라미터 값으로 설명될 수 있기 때문에 가능하다. 여기서, R-R 간격의 분포에 대한 감마 분포의 파라미터는 최우도 추정(maximum likelihood estimation) 방법에 의해 결정된다. R-R 간격은 ECG 파가 들어있는 유한 크기 창에서 추출되고, 감마 분포의 파라미터는 우도 함수를 최대화하는 방식으로 결정된다. 그 결과

개 의 R-R 간격들

에 대하여 파라미터 추정치

는 하기의 [수학식 1]로 계산된다. In an embodiment of the present invention, a method of classifying a heart condition is a parameter of a gamma distribution (

). here, (

) Determines the shape and scale of each gamma distribution. This analysis is possible because the interval between two arbitrary events can be explained by the appropriate parameter values of the gamma distribution. Here, the parameter of the gamma distribution with respect to the distribution of the RR interval is determined by a maximum likelihood estimation method. The RR interval is extracted from the finite size window containing the ECG wave, and the parameter of the gamma distribution is determined in such a way as to maximize the likelihood function. As a result

Dog RR intervals

Parameter estimate for

Is calculated by the following [Equation 1].

는 하기의 [수학식 2]로 계산된다.Parameter estimate

Is calculated by the following [Equation 2].

는 하기의 [수학식 3]과 같이 계산된다. here

Is calculated as shown in [Equation 3] below.

)의 값이 작아지면 비정상적인 ECG 파동의 가능성이 더 많이 존재함을 알 수 있다.As an example of estimating the parameter of the gamma distribution for this, a result of using the parameter estimation of the gamma distribution for a window of 30 seconds every 10 seconds in the MIT-BIH data set is shown in FIG. 5. In Fig. 5, 1) normal and abnormal classes are well separated by parameters of the gamma distribution, and 2) parameters of the gamma distribution (

), it can be seen that there is more possibility of abnormal ECG wave.

Times such as SDNN (Standard deviation of all NN intervals), SDANN (Standard Deviation of the 5 minute Average NN intervals), RMSSD (Root mean square of the successive differences) in conventional heart rate variability (HRV) analysis Geometric methods including domain features and HRV trigonometric exponents are often used. However, here, SDNN and RMSSD, which are easy to analyze for a short time, are compared with the method according to an embodiment of the present invention.

SDNN is given by the following [Equation 5].

는

번째 R-R 간격을 의미하고,

은 R-R 간격에 대한 평균을 의미한다.

Is

Mean th RR interval,

Means the average over the RR interval.

RMSSD is given by the following [Equation 6].

6 and 7 are diagrams illustrating the presence or absence of an abnormality in an ECG waveform according to an SDNN feature and an RMSSD feature in a method according to an embodiment of the present invention.

Results calculated using SDNN and RMSSD in the same manner as in the experiment of FIG. 5 are shown in FIGS. 6 and 7. These results show that the parameter of the gamma 7 distribution is more effective in discriminating abnormal ECG waves.

Meanwhile, the short-term analysis operation of ECG waves will be described.

에 가우시안 커널 함수가 할당된다. 여기서 로그 스케일된 감마 분포의 파라미터의 공간에서 주어진 입력 패턴

에 대하여 가우시안 커널 함수는 하기의 [수학식 7과 같이 주어진다. In an embodiment of the present invention, after estimating a parameter of a gamma distribution, two distributions representing normal and abnormal classes are determined in a space of parameters of the log-scaled gamma distribution. The center of each distribution to represent the two distributions

Is assigned a Gaussian kernel function. Where the input pattern given in the space of the parameters of the log scaled gamma distribution

With respect to the Gaussian kernel function is given by Equation 7 below.

는 공분산 행렬을 나타낸다. 파라미터 c 값은 분류 출력 (이 경우에는 베타 분포)의 적절한 분포를 찾는 방식으로 결정된다.Where c is a constant related to the variance of the Gaussian function

Denotes the covariance matrix. The value of parameter c is determined by finding an appropriate distribution of the classification output (beta distribution in this case).

The decision function for classifying the heart state is expressed as [Equation 8] below by a linear combination of Gaussian kernel functions.

는

번째 커널과 연결된 가중치를 의미한다.here

Is

Means the weight associated with the th kernel.

를 결정하여야 한다. 이를 위하여 선형 판별 분석(linear discriminant analysis, LDA) 을 적용할 수 있다. 먼저

개의 로그 스케일된 감마 분포의 파라미터의 공간에서 주어진 입력 패턴

에 대하여 커널에 대한 출력 패턴

을 결정한다. The next step is weighting so that normal and abnormal ECG waves can be identified.

Should be decided. To this end, linear discriminant analysis (LDA) can be applied. first

Input pattern given in the space of parameters of the log scaled gamma distribution

Output pattern to the kernel against

To decide.

및 비정상 패턴의 개수

의 합으로 볼 수 있다; 즉,

. 그러면 가중치 벡터

는 [수학식 9]와 같이 추정된다.Here, the total number of patterns is the number of normal patterns

And the number of abnormal patterns

Can be seen as the sum of; In other words,

. Then the weight vector

Is estimated as in [Equation 9].

,

,

은 각 각 정상과 비정상 패턴의 분포를 나타낸다.here

Represents the distribution of normal and abnormal patterns, respectively.

를 결정하면 심장 상태를 분류하는 결정 함수

가 결정된다. 그러면 결정 함수 값의 분포를 베타분포를 이용하여 파악하게 된다. 실제로 분류 모델의 분포는 분류 출력이 한정된 범위에 존재하고 단일 분포(unimodal distribution)를 갖는다는 가정 하에 베타 분포에 의해 근사될 수 있다. 이러한 가정 하에서, 출력 값을 0과 1 사이의 값으로 정규화 하면 임의의 무작위 변수(random variable)

에 대하여 베타 확률 밀도 함수(Beta probability density function)는 [수학식 10]과 같이 정의된다.Weight vector

Determining the deterministic function to classify the heart condition

Is determined. Then, the distribution of the value of the decision function is determined using the beta distribution. In practice, the distribution of the classification model can be approximated by the beta distribution, assuming that the classification output exists in a limited range and has a unimodal distribution. Under these assumptions, normalizing the output value to a value between 0 and 1 results in a random variable.

The beta probability density function is defined as [Equation 10].

는 베타 확률밀도 함수의 파라미터를 나타내고,

는 베타 함수로 [수학식 11]과 같이 정의된다.here

Represents the parameter of the beta probability density function,

Is a beta function and is defined as in [Equation 11].

And the beta cumulative distribution function is defined as [Equation 12].

는 모멘트 부합(moment matching) 방법으로 [수학식 13]과 같이 추정할 수 있다.Then the parameters of the beta probability density function

Can be estimated as [Equation 13] using a moment matching method.

는 각 각 정규 화된 결정 함수 값의 평균 및 분산을 의미한다. 이 방법은 샘플의 수가 작으면 부정확할 수도 있는데, 이런 경우 최우도 추정(maximum likelihood estimation) 방법으로 베타 확률밀도 함수의 파라미터를 결정할 수 있다.here

Denotes the mean and variance of each normalized decision function value. This method may be inaccurate if the number of samples is small. In this case, the parameter of the beta probability density function can be determined using a maximum likelihood estimation method.

8 is a view showing an LDA output histogram and beta variable estimation according to a class of an ECG waveform used in an embodiment of the present invention.

As an example, distribution of output values for normal and abnormal ECG waves and estimation of a beta probability density function accordingly are shown in FIG. 8.

을 하기의 [수학식 14]와 같이 결정하여 판단한다.On the other hand, after estimating the parameter of the beta distribution, the heart state classification apparatus 100 according to an embodiment of the present invention determines the normal or abnormal ECG wave using a beta cumulative distribution function. Significance probability for (p value)

Is determined as shown in [Equation 14] below.

은 각 각 정상 및 비정상에 클래스에 대한 무작위 변수를 의미한다.here

Means the random variable for each class in normal and abnormal, respectively.

을 하기의 [수학식 15]와 같이 구한다.Then, for a given RR interval, the determination of the normal or abnormal ECG wave is determined by comparing the significance probabilities of the hypotheses for normal and abnormal. That is, the probability for the normal class first

Is obtained as in [Equation 15] below.

Then, normal and abnormal classes are determined as shown in [Equation 16] below.

Here, a K-S (Kolmogorov-Smirnov) test may be performed to check whether the parameters of the estimated gamma or beta distribution are correct. As an example, the MIT-BIT data set was used to calculate the significance probability for the verification of each distribution by the K-S test (see Table 1). [Table 1] shows the significance probability for the verification of the gamma and beta distributions. As a result, a value much larger than the typical value (= 0.05) of the significance level for verification was obtained. In other words, it was found that the estimation of the parameters of the gamma and beta distributions fits well with the given data distribution. These results contribute to estimating more accurate class posterior probabilities for a given pattern in each classifier.

normal abnormal Gamma distribution 0.6083 0.5959 Beta distribution 0.3281 0.3410

In order to verify the validity of this method, the validity of an embodiment of the present invention was shown using the MIT-BIH data set. As a result, it was shown that the proposed method is not only effective in classifying heart conditions, but also more accurate classification than conventional classifiers such as k-NN and SVM. FIGS. 9 to 12 show heart abnormalities according to an embodiment of the present invention. It is a diagram showing the simultaneous occurrence of the current and next RR intervals according to the presence or absence.

9 and 10 show simultaneous occurrences of the current and next R-R intervals in the case of a steady state heart.

11 and 12 show simultaneous occurrence diagrams of the current and next R-R intervals in the case of an abnormal heart.

Meanwhile, a long-term analysis operation for a heart health state will be described.

가

개의 정상 ECG 파에 해당하는 R-R 간격의 시계열이라고 하면 현재 R-R 간격과 다음 R-R 간격 사이의 상관 계수

은 하기의 [수학식 17]과 같이 계산된다.Even in an abnormal heart condition, a normal ECG waveform may be temporarily generated, so long-term analysis is necessary. For this, the dynamics of cardiac activity are investigated. One of these methods can be used to examine the correlation coefficient between the current RR interval and the next RR interval. E.g

end

If the time series of RR intervals corresponding to normal ECG waves of dogs, the correlation coefficient between the current RR interval and the next RR interval

Is calculated as the following [Equation 17].

이다. here,

to be.

In order to confirm whether the correlation coefficient is effective in distinguishing between normal and abnormal hearts, examples showing the scatter plots for the current and next R-R intervals in the case of normal and abnormal heart conditions are shown in FIGS. 9 to 12. These examples show that in the case of a normal heart, two consecutive R-R intervals have a very high correlation, unlike in the case of an abnormal heart.

13 is a diagram illustrating a distribution of a correlation coefficient between a current and a next R-R interval according to the presence or absence of a heart abnormality according to an embodiment of the present invention.

In order to display this statistically, correlation coefficients for normal and abnormal heart conditions were collected, and their distribution was expressed as a histogram as shown in FIG. 13. In addition, the parameters of the beta probability density function were estimated from the correlation data of normal cardiac conditions. As a result, the values of the parameters of the beta distribution were given as a=41.8859, b=2.1833, and the significance probability value of the K-S test for the beta distribution fit was given as 0.4430, which is much higher than the standard significance level value of 0.05. Through this analysis, the determination of the heart condition for the R-R interval corresponding to the normal ECG wave of a given sequence is determined as follows.

1. Using the parameter of the estimated beta distribution, the significance probability is calculated as shown in [Equation 18] below.

(통상적인 값은 0.05)를 이용하여

이면 정상 심장 상태에 대한 가설을 수락하고, 그렇지 않으면, 정상 심장 상태의 가설을 기각한다.2. Standard significance level

(Typical value is 0.05)

If so, accept the hypothesis of a normal heart state, otherwise reject the hypothesis of a normal heart state.

The class probability output network using the beta distribution provides significant probabilities for each class, so that more accurate and consistent decisions can be made for short-term and long-term analysis of heart conditions.

On the other hand, an experiment on the presence or absence of an abnormality in the ECG wave will be described.

For the experiment of the method according to an embodiment of the present invention, ECG signal data from the MIT-BIH arrhythmia database was selected. The MIT-BIH arrhythmia database was selected from clinically important arrhythmias by two independent cardiologists, not only for normal beats, but also for abnormal beats, including Ventricular arrhythmia (VT), Ventricular Bigeminy (VB) and Ventricular fibrillation (VF) beats. Comments on and more bits are indicated. For this experiment, a window of 30 seconds for ECG signal data was selected, the R-R interval within the window was used as the input pattern, and the input pattern sequence sampled every 10 seconds was collected as a data set for NR and AN class classification. As a result, 3,198 NR and 1,565 AN pattern sets were used as data sets for NR and AN class classification.

로 추정하고, 로그 스케일된 감마 분포의 파라미터의 공간

에서 NR 및 AN 클래스에 대한 자료를 수집하였다. 그 후에 각 자료에 대하여 2차원 가우시안 함수의 변수를 구하고(여기서 c값은 0.3으로 결정), 각 가우시안 함수에 따른 가중치 값은 LDA 방법으로 결정하여 심장상태 분률 위한 결정 함수

를 구하였다. 그런 다음 각 NR 및 AN 클래스에 대한 결정 함수의 분포를 베타 파라미터

로 추정하여 NR 및 AN 클래스에 대한 분류기(CPON)를 구현하였다. 본 발명의 일 실시예에 따른 방법에서 감마 분포의 파라미터의 효과를 비교하기 위하여 HRV(heart rate variability) 분석에서 흔히 쓰이는 SDNN 및 RMSSD 특징을 사용하여 같은 방법으로 분류기(CPON)를 구현하였다. 또한 본 발명의 일 실시예에 따른 CPON 분류기는 로그 스케일 감마 분포의 파라미터의 동일한 입력 자료와 NR 및 AN 클래스 레이블의 출력 데이터를 사용하여 kNN 및 SVM 분류기와 같은 널리 사용되는 분류 모델과 비교하였다. 여기서 kNN 및 SVM 분류기는 Scikit-learn Python 라이브러리를 사용하였는데 kNN 분류기의 경우 k=1, 즉 가장 가까운 이웃을 사용하였고 SVM 분류기의 경우 선형 커널을 사용하여 지원 벡터를 선택하였다. In the method according to an embodiment of the present invention, the distribution of the RR interval in each 30-second window is a parameter of the gamma distribution.

Space of the parameters of the gamma distribution, estimated by and

Data for the NR and AN classes were collected in. After that, for each data, a variable of a two-dimensional Gaussian function is obtained (where c is determined as 0.3), and the weight value according to each Gaussian function is determined by the LDA method to determine the heart state fraction.

Was obtained. Then the distribution of the determinant function for each NR and AN class is determined by the beta parameter

We implemented a classifier (CPON) for the NR and AN classes. In order to compare the effect of the parameters of the gamma distribution in the method according to an embodiment of the present invention, a classifier (CPON) was implemented in the same manner by using SDNN and RMSSD features commonly used in heart rate variability (HRV) analysis. In addition, the CPON classifier according to an embodiment of the present invention was compared with widely used classification models such as kNN and SVM classifiers using the same input data of the parameters of the log scale gamma distribution and output data of the NR and AN class labels. Here, the kNN and SVM classifiers used the Scikit-learn Python library. In the case of the kNN classifier, k=1, that is, the nearest neighbor was used, and in the case of the SVM classifier, a support vector was selected using a linear kernel.

In this experiment, the evaluation of each classifier was evaluated with a 10-fold evaluation method for a given data set. That is, the NR and AN patterns were evenly divided into 10 parts, one of the 10 parts was used as test data, and the remaining 9 parts were used as training data to obtain classification performance of the test data. This process was repeated 10 times in total, with 10 parts used exactly once as test data. And as a result of the simulation, the average value of the classification performance for 10 data sets was determined.

측도의 네 가지 표준 성능 측정을 사용하였다.Classification performance as shown in [Equation 19] below, accuracy (accuracy), precision (precision), recall (recall) and

Four standard performance measures of the measure were used.

,

,

은 각각 진정한 양수, 진정한 음수, 거짓 양수 및 거짓 음수를 나타낸다. 이에 대한 시뮬레이션 결과는 각각 [표 2]와 [표 3]에 요약되어 있다. 이러한 결과는 1) 본 발명의 일 실시예에 따른 감마 분포의 파라미터가 다른 특징들(SDNN 및 RMSSD) 보다 높은 정확도와

측도에서 개선된 성능을 보여준다. 그리고 2) 본 발명의 일 실시예에 따른 클래스 확률 출력망(CPON)은 이러한 분류에 있어서 다른 분류기(k-NN 및 SVM)와 비교하여 매우 효과적임을 보여준다. 이와 더불어 본 발명의 일 실시예에 따른 클래스 확률 출력망은 NR 및 AN 클래스 테스트에 대하여 조건부 확률 값(즉, 유의확률)을 제공하는 반면에 k-NN 또는 SVM과 같은 판별 함수 기반 분류기는 정규 화된 측정값이 아닌 임의의 범위 안에서 존재하는 판별 값만 제공한다.here

Represents true positive, true negative, false positive and false negative numbers, respectively. The simulation results for this are summarized in [Table 2] and [Table 3], respectively. These results show that 1) the parameters of the gamma distribution according to an embodiment of the present invention have higher accuracy than other features (SDNN and RMSSD)

The measure shows improved performance. And 2) the class probability output network (CPON) according to an embodiment of the present invention shows that this classification is very effective compared to other classifiers (k-NN and SVM). In addition, the class probability output network according to an embodiment of the present invention provides conditional probability values (ie, significance probability) for NR and AN class tests, whereas a classifier based on a discriminant function such as k-NN or SVM is normalized. Only discrimination values that exist within an arbitrary range are provided, not measured values.

[Table 2] shows the classification performance of the CPON classifier according to each feature variable.

Characteristic variable Gamma parameter SDNN RMSSD accuracy 0.9733 0.9217 0.9221 + Class
(normal) Precision 0.9936 0.9944 0.9839 Recall 0.9665 0.8884 0.8987

0.9799 0.9384 0.9394 + Class
(abnormal) Precision 0.9352 0.8127 0.8241 Recall 0.9872 0.9898 0.9700

0.9605 0.8925 0.8911

[Table 3] shows the classification performance of each classifier using the parameter of the gamma distribution.

Classifier CPON kNN SVM accuracy 0.9733 0.9660 0.9704 + Class
(normal) Precision 0.9936 0.9798 0.9913 Recall 0.9665 0.9694 0.9644

0.9799 0.9745 0.9777 + Class
(abnormal) Precision 0.9352 0.9387 0.9310 Recall 0.9872 0.9591 0.9827

0.9605 0.9488 0.9562

On the other hand, the experiment on the presence or absence of abnormal heart health will be described. Experiments for long-term analysis of heart conditions were performed on the MIT-BIH normal sinus rhythm database (NSRDB), the MIT-BIH malignant ventricular arrhythmia database (VFDB) and the ECG signal data of the MIT-BIH atrial fibrous data. The NSRDB contains 18 long-term ECG waveform recordings from subjects without significant arrhythmia. The VFDB contains a 22-hour 30-minute ECG waveform recording of subjects experiencing episodes of persistent ventricular tachycardia (VT) and ventricular fibrillation (VF). The AFDB contains 25 long-term ECG recordings in the subject of persistent atrial fibrillation (AF) or atrial flutter.

[Table 4] shows experimental data for long-term analysis of the normal ECG waveform.

material Database Recording number Learning material NSRDB 16265, 16272, 16273, 16410, 16483, 16786, 16795, 17052, 17453, 18177 Test material NSRDB 18184, 19088, 19090, 19093, 19140
VFDB 418, 419, 420, 421, 422, 423, 424, 425, 428, 429, 602, 605, 607, 612, 614 AFDB 04015, 04048, 04746, 04908, 05121, 06426, 07162, 07879. 07910

측도의 측면에서의 성능이 평가되었다.For the time series set of NSRDB, the RR interval was used within a 30-minute window. Here, as shown in Table 4, the first 4 hours of each recording were used as data. Then, the correlation coefficient between the current and the next RR interval was collected, and the distribution of the correlation coefficient was estimated by the beta distribution parameter. As a result, a beta distribution with estimated parameters (a=41.8859, b=2.1833) was obtained. The corresponding p-value for the KS test for the beta distribution fit was calculated as 0.4430. In other words, it was found that the given data fit well with the beta distribution. In this regard, the distribution of the correlation coefficient and the estimated beta distribution of the RR time series are plotted in FIG. 13. Meanwhile, for a long-term analysis test of the heart condition, the RR interval corresponding to the normal ECG waveform within the 30-minute window was collected and the first 4 hours of each recording were used. Here, VFDB used the first 30 minutes, but in the case of VFDB, only 30 minutes of recording was given. For the given data, the correlation coefficient between the current and the next RR interval was calculated, and the significance probability for the steady state test was calculated using the beta distribution. Then, accuracy, precision, recall and classification of normal and abnormal heart conditions for three significance levels (0.05, 0.1, 0.2).

The performance in terms of measures was evaluated.

14 is a diagram illustrating a distribution of a significance probability (p-value) according to a class of a cardiac abnormality according to an embodiment of the present invention.

[Table 5] shows the discrimination performance of heart abnormalities using long-term analysis of the normal ECG waveform.

Significance level

accuracy 0.9677 0.9892 0.9677 Precision 0.9512 1.0000 1.0000 Recall 0.9750 0.9750 0.9250

0.9630 0.9873 0.9610

From these experimental results, it was found that the optimal classification performance was given at the significance level of 0.1. Specifically, the precision and recall measures were determined to be 1.00 and 0.975, respectively. This means that at a significance level of 0.1, the classifier's determination is 100% accurate when it is in a normal heart state, and only 2.5% of the normal heart state is not identified. That is, when the significance probability value is greater than or equal to 0.1, the reliability of the normal heart condition is very high. A histogram of the log-scaled p-value of the correlation coefficients for the NDRDB, AFDB and VFDB test sets is shown in FIG. 14 for comparison of the significance probability values of normal and abnormal heart conditions. This figure shows that the significance probability value is very small even when the ECG waveform is normal when the heart is in an abnormal state. In fact, the mean significance values of NR, AF and VT/VF in this test set were calculated as 0.5375, 0.045 and 0.0015, respectively. In conclusion, an embodiment of the present invention analyzes the RR interval of the ECG signal data by the parameter of the gamma distribution for classification of the heart condition, and uses the class probability output network (CPON) to determine the normal (NR) or abnormality of the ECG wave. Classify for (AN). According to an embodiment of the present invention, when the ECG wave is determined to be normal, the corresponding R-R interval is collected and the heart condition is further analyzed and confirmed. An embodiment of the present invention determines the heart state by calculating a correlation coefficient between the current and next R-R intervals for analysis thereof. Here, an embodiment of the present invention uses a conditional class probability value (ie, p-value) using a class probability output network (CPON) as a classifier for a heart condition. As a result, it was confirmed that even when the ECG wave was normal, the heart condition or the potential risk of the heart was classified in a consistent and reliable manner. In addition, the method according to an embodiment of the present invention is a handheld or wearable device capable of detecting the RR (or between the heartbeat and the heartbeat) interval of ECG signal data because it can be identified with a small number of parameters. It is easy to apply.

The above-described method for classifying a heart state based on a class probability output network according to the embodiments of the present invention may be implemented as a computer-readable code on a computer-readable recording medium. The method for classifying a heart state based on a class probability output network according to embodiments of the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable recording medium.

A non-transitory computer-readable storage medium including at least one program executable by a processor, wherein the at least one program, when executed by the processor, causes the processor to: gamma indicating a statistical characteristic of an interval of an electrocardiogram signal The parameters of the distribution are estimated, the distance between the estimated gamma distribution parameter and the center point of the pre-learned gamma distribution parameter is calculated, and the distance between the calculated center point is input to the class probability output network to provide normal and unsteady classes. A non-transitory computer-readable storage medium comprising instructions for determining a significance probability of a class and comparing the determined significance probability of the normal class and the abnormal class to each other to classify an ECG wave as a normal wave or an abnormal wave may be provided. have.

The above-described method according to the present invention may be implemented as a computer-readable code on a computer-readable recording medium. The computer-readable recording medium includes all types of recording media in which data that can be decoded by a computer system is stored. For example, there may be read only memory (ROM), random access memory (RAM), magnetic tape, magnetic disk, flash memory, optical data storage device, and the like. In addition, the computer-readable recording medium can be distributed in a computer system connected through a computer communication network, and stored and executed as code that can be read in a distributed manner.

Although described above with reference to the drawings and examples, it does not mean that the protection scope of the present invention is limited by the drawings or examples, and those skilled in the art It will be appreciated that various modifications and changes can be made to the present invention without departing from the spirit and scope.

Specifically, the described features may be implemented in digital electronic circuitry, or computer hardware, firmware, or combinations thereof. Features may be executed in a computer program product implemented in storage in a machine-readable storage device, for example, for execution by a programmable processor. And the features can be performed by a programmable processor executing a program of directives to perform the functions of the described embodiments by operating on input data and generating output. The described features include at least one programmable processor, at least one input device, and at least one output coupled to receive data and directives from the data storage system and to transmit data and directives to the data storage system. It can be executed within one or more computer programs that can be executed on a programmable system including the device. A computer program includes a set of directives that can be used directly or indirectly within a computer to perform a specific action on a given result. A computer program is written in any form of a programming language, including compiled or interpreted languages, and is included as a module, element, subroutine, or other unit suitable for use in another computer environment, or as a independently operable program. It can be used in any form.

Suitable processors for execution of a program of directives include, for example, both general and special purpose microprocessors, and either a single processor or multiple processors of a different kind of computer. Storage devices suitable for implementing computer program directives and data implementing the described features are, for example, semiconductor memory devices such as EPROM, EEPROM, and flash memory devices, magnetic devices such as internal hard disks and removable disks. Devices, magneto-optical disks, and all types of non-volatile memory including CD-ROM and DVD-ROM disks. The processor and memory may be integrated within application-specific integrated circuits (ASICs) or added by ASICs.

The present invention described above is described on the basis of a series of functional blocks, but is not limited by the above-described embodiments and the accompanying drawings, and various substitutions, modifications and changes within the scope not departing from the technical spirit of the present invention It will be apparent to those of ordinary skill in the art to which this invention pertains.

Combinations of the above-described embodiments are not limited to the above-described embodiments, and combinations of various types as well as the above-described embodiments may be provided according to implementation and/or need.

In the above-described embodiments, the methods are described on the basis of a flow chart as a series of steps or blocks, but the present invention is not limited to the order of steps, and certain steps may occur in a different order or concurrently with other steps as described above. I can. In addition, those of ordinary skill in the art understand that the steps shown in the flowchart are not exclusive, other steps are included, or one or more steps in the flowchart may be deleted without affecting the scope of the present invention. You can understand.

The foregoing embodiments include examples of various aspects. Although not all possible combinations for representing the various aspects can be described, those of ordinary skill in the art will recognize that other combinations are possible. Accordingly, the present invention will be said to cover all other replacements, modifications and changes falling within the scope of the following claims.

101: heart rate detector
100: heart condition classification device
110: receiving module
120: memory
130: processor

Claims (21)

In the heart state classification method performed by the heart state classification device,
Estimating a parameter of a gamma distribution indicating a statistical characteristic of an interval of an electrocardiogram signal;
Calculating a distance between the estimated parameter of the gamma distribution and a center point of the parameter of the previously learned gamma distribution;
Determining a significance probability of a normal class and an abnormal class by inputting the calculated distance between the center points into a class probability output network; And
And classifying the ECG signal as a normal wave or an abnormal wave by comparing the determined significance probabilities of the normal class and the abnormal class with each other. The method of claim 1,
The interval of the ECG signal is,
A method for classifying a heart condition based on a class probability output network, which is an RR interval of the ECG signal or a beat-to-beat interval. The method of claim 1,
Calculating the distance between the center points,
A method for classifying a heart state based on a class probability output network for calculating a distance between the estimated parameter of the gamma distribution and the center point of the parameter of the previously learned gamma distribution on a log scale. The method of claim 1,
The calculated distance between the center points is output by a kernel function and input to a class probability output network. The method of claim 1,
The step of determining the significance probability,
A class probability output network that allocates a Gaussian kernel function to the distance between the calculated center points, and calculates a decision function for a normal class and an abnormal class for classifying a heart state by determining a weight value according to the allocated Gaussian kernel function Based heart condition classification method. The method of claim 5,
The step of determining the significance probability,
A method for classifying a heart state based on a class probability output network for estimating the calculated distribution of the decision function for the normal class and the abnormal class as a parameter of a beta distribution. The method of claim 6,
The step of determining the significance probability,
A method for classifying a heart state based on a class probability output network for determining a significance probability for a hypothesis for a normal class and an abnormal class using a beta cumulative distribution function in which the parameter of the estimated beta distribution is reflected. The method of claim 1,
When the ECG signal is classified as a normal wave, an interval of the normal ECG signal is additionally collected to calculate a correlation coefficient between the current interval and the next interval, and the heart state is determined as a normal state or an abnormal state using the calculated correlation coefficient value. A method for classifying a heart state based on a class probability output network, further comprising determining as. The method of claim 8,
The step of determining the heart state as a normal state or an abnormal state,
Applying the calculated correlation coefficient value to a pre-learned beta distribution to calculate a significance probability for a steady state with a class probability output network, and determining the heart state as a normal state or an abnormal state using the calculated significance probability. , Class probability output network based cardiac state classification method. The method of claim 9,
The step of determining the heart state as a normal state or an abnormal state,
When the calculated significance probability is greater than or equal to a threshold value, the cardiac state is determined as a normal state. A memory for storing at least one program; And
Including a processor connected to the memory,
The processor, by executing the at least one program,
Estimate a parameter of the gamma distribution representing the statistical characteristics of the interval of the ECG signal,
Calculate a distance between the estimated parameter of the gamma distribution and the center point of the parameter of the previously learned gamma distribution,
Inputting the calculated distance between the center points into a class probability output network to determine the significance probability of the normal class and the abnormal class,
Class probability output network-based cardiac state classification apparatus for classifying an electrocardiogram wave as a normal wave or an abnormal wave by comparing the determined significance probability of the normal class and the abnormal class with each other. The method of claim 11,
The interval of the ECG signal is,
An RR interval of the ECG signal or a beat-to-beat interval of the ECG signal. The method of claim 11,
The processor,
A cardiac state classification apparatus based on a class probability output network for calculating a distance between the estimated parameter of the gamma distribution and the center point of the parameter of the previously learned gamma distribution on a log scale. The method of claim 11,
The calculated distance between the center points is output by a kernel function and input to a class probability output network. The method of claim 11,
The processor,
A class probability output network that allocates a Gaussian kernel function to the distance between the calculated center points, and calculates a decision function for a normal class and an abnormal class for classifying a heart state by determining a weight value according to the allocated Gaussian kernel function Based heart condition classification device. The method of claim 15,
The processor,
A class probability output network-based cardiac state classification apparatus for estimating the calculated distribution of the decision function for the normal class and the abnormal class as a parameter of a beta distribution. The method of claim 16,
The processor,
A cardiac state classification apparatus based on a class probability output network for determining a significance probability for a hypothesis for a normal class and an abnormal class using a beta cumulative distribution function in which the parameter of the estimated beta distribution is reflected. The method of claim 11,
The processor,
When the ECG signal is classified as a normal wave, an interval of the normal ECG signal is additionally collected to calculate a correlation coefficient between the current interval and the next interval, and the heart state is determined as a normal state or an abnormal state using the calculated correlation coefficient value. Class probability output network-based cardiac state classification device determined by. The method of claim 18,
The processor,
Applying the calculated correlation coefficient value to a pre-learned beta distribution to calculate a significance probability for a steady state with a class probability output network, and determining the heart state as a normal state or an abnormal state using the calculated significance probability. , Class probability output network based cardiac state classification device. The method of claim 19,
The processor,
If the calculated significance probability is greater than or equal to a threshold value, the cardiac state classification apparatus based on a class probability output network determines the heart state as a normal state. A non-transitory computer-readable storage medium comprising at least one program executable by a processor, wherein the at least one program, when executed by the processor, causes the processor to:
Estimate a parameter of the gamma distribution representing the statistical characteristics of the interval of the ECG signal,
Calculate a distance between the estimated parameter of the gamma distribution and the center point of the parameter of the previously learned gamma distribution,
Inputting the calculated distance between the center points into a class probability output network to determine the significance probability of the normal class and the abnormal class,
And instructions for classifying an electrocardiogram wave as a normal wave or an abnormal wave by comparing the determined significance probability of the normal class and the abnormal class with each other.

Images