阅读说明：本技术 一种房颤事件检测方法 (Atrial fibrillation event detection method ) 是由 赵卫 周成龙 于 2020-07-22 设计创作，主要内容包括：本发明提供了一种房颤事件检测方法,其可快速分析高通量心电数据并提供较高的准确率,达到减轻人工工作量、提高医生对房颤诊断效率的目的；其包括以下步骤：S1、获取用于房颤事件检测的心电信号,随后对心电信号进行预处理以去除干扰和无效数据；S2、对预处理后的心电信号进行QRS检波处理；S3、根据QRS检波处理结果进行高阶统计量统计而得到房颤系数,并根据QRS检波结果动态获取心率基本系数；S4、根据所述步骤S3中得到的房颤系数和心率基本系数进行房颤判定规则的适配,若房颤系数和心率基本系数满足设定的房颤判定规则适配条件,则判定为房颤,若不满足,判定为非房颤,从而获得房颤判定结果。(The invention provides an atrial fibrillation event detection method, which can quickly analyze high-flux electrocardio data and provide higher accuracy, and achieves the purposes of reducing the manual workload and improving the diagnosis efficiency of doctors on atrial fibrillation; which comprises the following steps: s1, acquiring an electrocardiosignal for atrial fibrillation event detection, and then preprocessing the electrocardiosignal to remove interference and invalid data; s2, carrying out QRS detection processing on the preprocessed electrocardiosignals; s3, carrying out high-order statistic statistics according to the QRS detection processing result to obtain an atrial fibrillation coefficient, and dynamically acquiring a heart rate basic coefficient according to the QRS detection result; and S4, adapting an atrial fibrillation judgment rule according to the atrial fibrillation coefficient and the heart rate basic coefficient obtained in the step S3, judging that the atrial fibrillation is the atrial fibrillation if the atrial fibrillation coefficient and the heart rate basic coefficient meet the set adaptation condition of the atrial fibrillation judgment rule, and judging that the atrial fibrillation is not the atrial fibrillation if the atrial fibrillation coefficient and the heart rate basic coefficient do not meet the set adaptation condition of the atrial fibrillation judgment rule, thereby obtaining an atrial fibrillation judgment result.)

1. An atrial fibrillation event detection method is characterized by comprising the following steps of:

s1, acquiring an electrocardiosignal for atrial fibrillation event detection, and then preprocessing the electrocardiosignal to remove interference and invalid data;

s2, carrying out QRS detection processing on the preprocessed electrocardiosignals;

s3, carrying out high-order statistic statistics according to the QRS detection processing result to obtain an atrial fibrillation coefficient, and dynamically acquiring a heart rate basic coefficient according to the QRS detection result;

and S4, adapting an atrial fibrillation judgment rule according to the atrial fibrillation coefficient and the heart rate basic coefficient obtained in the step S3, judging that the atrial fibrillation is the atrial fibrillation if the atrial fibrillation coefficient and the heart rate basic coefficient meet the set adaptation condition of the atrial fibrillation judgment rule, and judging that the atrial fibrillation is not the atrial fibrillation if the atrial fibrillation coefficient and the heart rate basic coefficient do not meet the set adaptation condition of the atrial fibrillation judgment rule, thereby obtaining an atrial fibrillation judgment result.

2. The method for detecting atrial fibrillation events according to claim 1, wherein in step S1, the preprocessing includes: and removing the high-frequency burr noise signal through a low-pass filter, removing the baseline drift interference signal through a high-pass filter, and removing the 50Hz power frequency interference signal through a wave trap.

3. The method of claim 1, wherein in step S2, the QRS detection process comprises the following steps:

s2.1, positioning QRS heart beat: acquiring QRS position information of heart beats, wherein if a standard database is adopted, the R wave position number on an electrocardiogram is directly acquired from a standard marking file given by the standard database, and if the standard database is adopted, the Hamilton-Tompkins heart beat positioning algorithm is adopted to acquire the R wave position information of the heart beats in the electrocardio recording data so as to acquire heart beat QRS heart beat positioning;

s2.2, RR interval calculation: after the positioning of the QRS heart beat is obtained, the distance between the R points of adjacent QRS waves is the interval of adjacent heart beats, so that QRS detection processing is realized, and RR interval data of electrocardiosignals are obtained.

4. The method of claim 3, wherein in step S3, the statistical processing of the high order statistics of the sliding window is performed according to the QRS detection result, that is, the sliding window is performed with the set start position and window width as the sliding window, and the sliding window processing is performed with the set window sliding step size, and the high order statistics are performed in each sliding window.

5. The method of claim 4, wherein in step S3, the calculation of the high order statistic comprises the following steps:

s3.1, by formula dRR_(i)＝RR_(i+1)-RR_(i)To obtain a difference dRR between two adjacent RR intervals_(i)Wherein RR_(i)RR interval data for heartbeats within the current sliding window, RR_(i+1)Is equal to RR_(i)Adjacent RR interval data, i 1, 2, 3,. . . . . . N, N is the number of RR intervals in the current sliding window;

s3.2, dRR_(i)Corresponding RR_(i)Interval data constitute data pairs (RR)_(i)，dRR_(i)) Then by calculation of formula

Calculate Joint Entropy Joint int Encopy (RR)_(i),dRR_(i)) And realizing high-order statistic calculation.

6. The method for detecting atrial fibrillation events according to claim 5, wherein in step S3, the formula is calculated as follows:

the atrial fibrillation coefficient afIndex is calculated.

7. The method for detecting atrial fibrillation events according to claim 5, wherein in step S3, the formula is calculated as follows:

8. The method for detecting atrial fibrillation events of claim 1, wherein in step S4, the obtained atrial fibrillation determination result is compared with the standard atrial fibrillation labeling result by the WFDB tool provided by MIT to obtain sensitivity and specificity, and then whether the obtained sensitivity and specificity result meets the expectation, i.e. is within the standard labeled atrial fibrillation segment, if yes, the test determination is ended, if not, the adaptation condition of the atrial fibrillation determination rule is adjusted, and the step S3 is repeated.

Technical Field

The invention relates to the technical field of atrial fibrillation detection, in particular to an atrial fibrillation event detection method.

Background

Atrial fibrillation is a common arrhythmia problem, is serious atrial electrical activity disorder, and the incidence rate of atrial fibrillation is continuously increased along with the increase of age, but the atrial fibrillation not only affects the life quality of patients, but also can cause thromboembolism, heart failure and cerebral apoplexy in severe cases. Along with the development of long-term electrocardio monitoring, the obtained electrocardiosignal data volume is larger and larger, and great challenge is brought to the traditional work of diagnosing atrial fibrillation by manually interpreting electrocardio data. At present, a method capable of rapidly analyzing a large amount of electrocardiogram data and having a high atrial fibrillation detection accuracy rate is needed, and a doctor is helped to improve the efficiency of atrial fibrillation diagnosis.

Disclosure of Invention

Aiming at the problems, the invention provides an atrial fibrillation event detection method which can quickly analyze high-throughput electrocardiogram data and provide higher accuracy, and achieves the purposes of reducing the manual workload and improving the diagnosis efficiency of doctors on atrial fibrillation.

The technical scheme is as follows: an atrial fibrillation event detection method is characterized by comprising the following steps of:

s1, acquiring an electrocardiosignal for atrial fibrillation event detection, and then preprocessing the electrocardiosignal to remove interference and invalid data;

s2, carrying out QRS detection processing on the preprocessed electrocardiosignals;

s3, carrying out high-order statistic statistics according to the QRS detection processing result to obtain an atrial fibrillation coefficient, and dynamically acquiring a heart rate basic coefficient according to the QRS detection result;

and S4, adapting an atrial fibrillation judgment rule according to the atrial fibrillation coefficient and the heart rate basic coefficient obtained in the step S3, judging that the atrial fibrillation is the atrial fibrillation if the atrial fibrillation coefficient and the heart rate basic coefficient meet the set adaptation condition of the atrial fibrillation judgment rule, and judging that the atrial fibrillation is not the atrial fibrillation if the atrial fibrillation coefficient and the heart rate basic coefficient do not meet the set adaptation condition of the atrial fibrillation judgment rule, thereby obtaining an atrial fibrillation judgment result.

It is further characterized in that:

further, in the step S1, the preprocessing includes: removing high-frequency burr noise signals through a low-pass filter, removing baseline drift interference signals through a high-pass filter, and removing 50Hz power frequency interference signals through a wave trap;

further, in the step S2, the QRS detection processing includes the steps of:

s2.1, positioning QRS heart beat: acquiring QRS position information of heart beats, wherein if a standard database is adopted, the R wave position number on an electrocardiogram is directly acquired from a standard marking file given by the standard database, and if the standard database is adopted, the Hamilton-Tompkins heart beat positioning algorithm is adopted to acquire the R wave position information of the heart beats in the electrocardio recording data so as to acquire heart beat QRS heart beat positioning;

s2.2, RR interval calculation: after the positioning of the heart QRS heart beat is obtained, the distance between the R points of adjacent QRS waves is an adjacent heart beat interval, so that QRS detection processing is realized, and RR interval data of electrocardiosignals are obtained;

further, in step S3, performing sliding window high order statistic statistics processing according to the QRS detection processing result, that is, performing sliding window processing with the set start position and window width as a sliding window and the set window sliding step length, and performing high order statistic statistics in each sliding window;

further, in the step S3, the calculation of the high order statistic includes the following steps:

s3.1, by formula dRR_(i)＝RR_(i+1)-RR_(i)To obtain a difference dRR between two adjacent RR intervals_(i)Wherein RR_(i)RR interval data for heartbeats within the current sliding window, RR_(i+1)Is equal to RR_(i)Adjacent RR interval data, i 1, 2, 3,. . . . . . N, N is the number of RR intervals in the current sliding window;

s3.2, dRR_(i)Corresponding RR_(i)Interval data constitute data pairs (RR)_(i)，dRR_(i)) Then by calculation of formula

Calculating joint Entropy jo int Encopy (RR)_(i),dRR_(i)) Realizing the calculation of high-order statistics;

further, in the step S3, by a calculation formula:

calculating an atrial fibrillation coefficient af Index;

further, in the step S3, by a calculation formula:calculating an average RR intervalThereby obtaining a heart rate basic coefficient;

further, in step S4, the obtained atrial fibrillation determination result is compared with the standard atrial fibrillation labeling result by the WFDB tool provided by MIT to obtain sensitivity and specificity, and then it is determined whether the obtained sensitivity and specificity result meets expectations, that is, whether the obtained sensitivity and specificity result is within the standard labeled atrial fibrillation segment, if yes, the test determination is ended, if not, the adaptation condition of the atrial fibrillation determination rule is adjusted, and step S3 is repeated.

The method has the advantages that firstly, the acquired electrocardiosignals are preprocessed to remove interference and invalid data, then the processed electrocardiosignals are subjected to QRS detection processing, atrial fibrillation coefficients and basic heart rate coefficients are obtained according to the QRS detection processing results, after atrial fibrillation is judged according to the obtained atrial fibrillation coefficients and basic heart rate coefficients, atrial fibrillation judgment results, namely atrial fibrillation diagnosis, can be obtained quickly and efficiently, and the method has good application and popularization values.

Drawings

FIG. 1 is a flow chart of the present invention;

FIG. 2 is a schematic diagram of RR intervals within a sliding window.

Detailed Description

As shown in fig. 1 and fig. 2, the method for detecting atrial fibrillation events of the present invention includes the following steps:

s1, acquiring electrocardiosignals for atrial fibrillation event detection, and then preprocessing the electrocardiosignals (namely ECG signals) to remove interference and invalid steady-state noise signals so as to prevent the interference signals from causing adverse effects in subsequent data processing;

the pretreatment comprises the following steps: and removing the high-frequency burr noise signal through a low-pass filter, removing the baseline drift interference signal through a high-pass filter, and removing the 50Hz power frequency interference signal through a wave trap.

S2, carrying out QRS detection processing on the preprocessed electrocardiosignals by using a difference threshold method (the conventional detection method);

the QRS detection processing comprises the following steps:

s2.1, QRS heart beat positioning, wherein the QRS wave complex is a significant characteristic wave complex of a heart beat, QRS wave complex detection is the basis of subsequent high-order statistical data, heart beat information in an electrocardiosignal is extracted through QRS heart beat positioning, and then an RR interval of the heart beat is obtained, specifically, QRS position information of the heart beat is obtained firstly, if a standard database is adopted, the R wave position number on an electrocardiogram is directly obtained from a standard marking file given by the standard database, and if the heart beat is recorded by an electrocardiosignal which is not marked in a standard way, a Hamilton-Tompkins heart beat positioning algorithm is adopted to obtain heart beat R wave position information in the electrocardiorecord data, so that heart beat QRS heart beat positioning is obtained;

s2.2, RR interval calculation: after the positioning of the heart QRS heart beat is obtained, the distance between the R points of adjacent QRS waves is an adjacent heart beat interval, so that QRS detection processing is realized, and RR interval data of electrocardiosignals are obtained; the RR interval is important information reflecting heart rhythm, high-order statistics of the RR interval can reflect the regular condition of heart pulsation, and the RR interval refers to the time limit between two R waves on an electrocardiogram; in fig. 2, QRS_(i-1)、QRS_(i)、QRS_(i+1)The adjacent QRS waves.

S3, carrying out sliding window high-order statistic statistical processing according to QRS detection processing results to reflect the difference between the RR interval distribution of the normal state and the atrial fibrillation state, specifically, taking a set initial position and window width as a sliding window, carrying out sliding window processing through a set window sliding step length, and carrying out high-order statistic statistical processing in each sliding window to obtain an atrial fibrillation coefficient and a heart rate basic coefficient; when the high-order statistic statistics is carried out, abnormal heart beat types are screened, and parameters of abnormal and invalid heart beats do not participate in the high-order statistic statistics, so that the atrial fibrillation detection result is prevented from being interfered.

Specifically, the calculation of the higher order statistic comprises the following steps:

s3.1, by formula dRR_(i)＝RR_(i+1)-RR_(i)To obtain a difference dRR between two adjacent RR intervals_(i)Wherein RR_(i)RR interval data for heartbeats within the current sliding window, RR_(i+1)Is equal to RR_(i)Adjacent RR interval data, i 1, 2, 3,. . . . . . N, N is the number of RR intervals in the current sliding window;

s3.2, dRR_(i)Corresponding RR_(i)Interval data constitute data pairs (RR)_(i)，dRR_(i)) Therefore, the current heart beat interval can be embodied, the difference value between the heart beat interval and the previous heart beat interval can be embodied, the deficiency of RR interval data time sequence information when calculating high-order statistic is compensated to a certain extent, and then a calculation formula is used for calculating the RR interval data time sequence information

Calculate Joint Entropy Joint int Encopy (RR)_(i),dRR_(i)) Realizing the calculation of high-order statistics;

because atrial fibrillation is a quick arrhythmia, the heart rate is very fast when atrial fibrillation takes place usually, consequently if this high order statistics of direct use joint entropy detects atrial fibrillation, then lack expert's experience information, then carry out a non-linear transformation with joint entropy, reflect the very fast condition of heart rate under the atrial fibrillation general condition, when the heart rate is very fast, reinforcing atrial fibrillation coefficient, relatively weaken the atrial fibrillation coefficient when the heart rate is less, then through the computational formula:

calculating an atrial fibrillation coefficient af Index;

and finally, selecting heart beats in the current sliding window to calculate an average RR interval to reflect the average heart rate of the current sliding window state, and calculating the average RR interval according to a calculation formula:calculating an average RR intervalThus obtaining the heart rate basic coefficient.

And S4, adapting the atrial fibrillation judgment rule according to the atrial fibrillation coefficient and the heart rate basic coefficient obtained in the step S3, judging that the atrial fibrillation is the atrial fibrillation if the atrial fibrillation coefficient and the heart rate basic coefficient meet the set adaptation condition of the atrial fibrillation judgment rule, and judging that the atrial fibrillation is not the atrial fibrillation if the atrial fibrillation coefficient and the heart rate basic coefficient do not meet the set adaptation condition of the atrial fibrillation judgment rule, thereby obtaining an atrial fibrillation judgment result.

Subsequently, the atrial fibrillation determination result is verified, namely the obtained atrial fibrillation determination result is compared with a standard atrial fibrillation labeling result through a WFDB tool provided by MIT (MIT identification), wherein the obtained atrial fibrillation determination result needs to be embodied in the form of a test labeling file, and the test labeling file needs to be completely consistent with the labeling file format of MIT-BIH AFDB, so that the WFDB tool provided by MIT is used for evaluating the atrial fibrillation detection result, the atrial fibrillation results are compared heart beat by heart beat, the heart beat determined as atrial fibrillation is predicted, if the heart beat is in a standard marked atrial fibrillation segment, a true-true example is given, otherwise, a false-true example is given; predicting the heartbeat judged as non-atrial fibrillation, if the heartbeat is in an atrial fibrillation segment marked by a standard, determining a false negative example, otherwise, determining a true negative example, and obtaining sensitivity and specificity respectively of 96.72% and 93.98% according to a heartbeat-by-heartbeat comparison result (the sensitivity and specificity are basic comparison methods in the industry and are an existing calculation mode), then judging whether the sensitivity and specificity result meets expectations (the expectation can be a set expectation, if the obtained sensitivity and specificity result is 80%, the result is judged not to meet the expectation, if the obtained sensitivity and specificity result is 90%, the result is judged to meet the expectation and can be set according to actual conditions), if the result meets the expectation, finishing the test, if the result does not meet the expectation, adjusting an atrial fibrillation judgment rule adaptation condition, and repeating the step S3; the atrial fibrillation judgment rule adapting conditions are adjusted mainly according to different heart rate basic coefficients, the classification threshold values of the atrial fibrillation are adjusted, specific adjusting coefficients are obtained through data experiments, and the adapting conditions of the atrial fibrillation judgment rules are correspondingly adjusted according to actual conditions.