2024年 05期

针对心律失常诊断算法中存在的不平衡数据集诊断准确率及阳性预测值较低的问题,提出一种基于优化自适应模型的心律失常辅助诊断方法;提取心电信号的77维特征并将其融合,使用融合特征训练诊断模型,同时利用改进的粒子群算法优化自适应模型参数;采用优化模型对MIT-BIH心律失常数据库进行诊断实验并与现有方法进行对比。结果表明,本文所提方法在测试数据集的诊断准确率达到98.2%,正常或束支传导阻滞节拍、室上性异常节拍、心室异常节拍、融合节拍的阳性预测值分别达到98.5%、 96.1%、 95.5%、 92.0%,诊断准确率和阳性预测值明显大于现有方法的。


摘要(Abstract):

针对心律失常诊断算法中存在的不平衡数据集诊断准确率及阳性预测值较低的问题,提出一种基于优化自适应模型的心律失常辅助诊断方法;提取心电信号的77维特征并将其融合,使用融合特征训练诊断模型,同时利用改进的粒子群算法优化自适应模型参数;采用优化模型对MIT-BIH心律失常数据库进行诊断实验并与现有方法进行对比。结果表明,本文所提方法在测试数据集的诊断准确率达到98.2%,正常或束支传导阻滞节拍、室上性异常节拍、心室异常节拍、融合节拍的阳性预测值分别达到98.5%、 96.1%、 95.5%、 92.0%,诊断准确率和阳性预测值明显大于现有方法的。

关键词(KeyWords): 心律失常诊断;特征融合;心电信号;自适应提升模型;粒子群优化算法

基金项目(Foundation): 国家自然科学基金项目(62271230)

作者(Author): 张晴,蒋萍,杨金广,李天宝,于刚

DOI: 10.13349/j.cnki.jdxbn.20240312.002

参考文献(References):

[1] LIN C C,YANG C M.Heartbeat classification using normalized RR intervals and morphological features[J].Mathematical Problems in Engineering,2014,2014:712474.

[2] CHEN S S,HUA W,LI Z,et al.Heartbeat classification using projected and dynamic features of ECG signal[J].Biomedical Signal Processing and Control,2017,31:165.

[3] FILOS D,CHOUVARDA I,TACHMATZIS D,et al.Beat-to-beat P-wave morphology as a predictor of paroxysmal atrial fibrillation[J].Computer Method and Programs in Biomedicine,2017,151:111.

[4] QIN Q,LI J Q,ZHANG L,et al.Combining low-dimensional wavelet features and support vector machine for arrhythmia beat classification[J].Scientific Reports,2017,7(1):6067.

[5] KALIDAS V,TAMIL L S.Detection of atrial fibrillation using discrete-state Markon models and random forests[J].Computers in Biology and Medicine,2019,113:103386.

[6] ADNANE M,BELOUCHRANI A.Heartbeats classification using QRS and T waves autoregressive features and RR interval features[J].Expert Systems,2017,34 (6):e12219.

[7] JI S S,LI R C,SHEN S Y,et al.Heartbeat classification based on multifeature combination and stacking-DWKNN algorithm[J].Journal of Healthcare Engineering,2021,2021:8811837.

[8] ZHU W L,CHEN X H,WANG Y,et al.Arrhythmia recognition and classification using ECG morphology `and segment feature analysis[J].IEEE/ACM Transactions on Computational Biology and Bioinformatics,2019,16(1):131.

[9] LI H Q,FENG X L,CAO L,et al.A new ECG signal classification based on WPD and ApEn feature extraction[J].Circuits,Systems,and Signal Processing,2016,35(1):339.

[10] SHARMA M,TAN R S,ACHARYA U R.Automated heartbeat classification and detection of arrhythmia using optimal orthogonal wavelet filters[J].Informatics in Medicine Unlocked,2019,16:100221.

[11] MOHEBBANAAZ,RAJANI KUMARI L V,PADMA SAI Y.Classification of arrhythmia beats using optimized k-nearest neighbor classifier[M]//UDGATA S K,SETHI S,SRIRAMA S N.Intelligent Systems:Lecture Notes in Networks and Systems,Vol 185.Singapore:Springer,2021:349.

[12] KIRANYAZ S,INCE T,GABBOUJ M.Real-time patient-specific ECG classification by 1-D convolutional neural networks[J].IEEE Transactions on Biomedical Engineering,2016,63(3):664.

[13] ACHARYA U R,OH S L,HAGIWARA Y,et al.A deep convolutional neural network model to classify heartbeats[J].Computers in Biology and Medicine,2017,89:389.

[14] YILDIRIM ?.A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification[J].Computers in Biology and Medicine,2018,96:189.

[15] MARTIN H,IZQUIERDO W,CABRERIZO M,et al.Near real-time single-beat myocardial infarction detection from single-lead electrocardiogram using long short-term memory neural network[J].Biomedical Signal Processing and Control,2021,68:102683.

[16] MONDéJAR-GUERRA V,NOVO J,ROUCO J,et al.Heartbeat classification fusing temporal and morphological information of ECGs via ensemble of classifiers[J].Biomedical Signal Processing and Control,2019,47:41.

[17] 陶亮,刘宝宁,梁玮.基于CNN-LSTM 混合模型的心律失常自动检测[J].山东大学学报(工学版),2021,51(3):30.

[18] XIE T T,LI R C,SHEN S Y,et al.Intelligent analysis of premature ventricular contraction based on features and random forest[J].Journal of Healthcare Engineering,2019,2019:5787582.

[19] GAJOWNICZEK K,GRZEGORCZYK I,ZABKOWSKI T,et al.Weighted random forests to improve arrhythmia classification[J].Electronics,2020,9(1):99.

[20] YANG P,WANG D,ZHAO W B,et al.Ensemble of kernel extreme learning machine based random forest classifiers for automatic heartbeat classification[J].Biomedical Signal Processing and Control,2021,63:102138.

[21] DE CHAZAL P,O’DWYER M,REILLY R B.Automatic classification of heartbeats using ECG morphology and heartbeat interval features[J].IEEE Transactions on Biomedical Engineering,2004,51(7):1196-1198.

[22] 马金伟.基于深度学习的心电信号识别分类算法研究[D].重庆:重庆理工大学,2019:23-25.

[23] 孙宏健.基于特征融合的心电信号房颤自动检测算法研究[D].济南:山东大学,2021:16-17.

[24] 闫红梅,何明一.基于聚类和联合偏度与峰度指数的高光谱数据波段选择算法[J].信号处理,2023,39(1):4.

[25] KAYA Y,UYAR M,TEKIN R,et al.1D-local binary pattern based feature extraction for classification of epileptic EEG signals[J].Applied Mathematics & Computation,2014,243:212.

[26] HASTIE T,ROSSET S,ZHU J,et al.Multi-class adaboost[J].Statistics and Its Interface,2009,2(3):351-353.

[27] 张均.基于粒子群寻优的AdaBoost算法研究[D].宁波:宁波大学,2020.

[28] LIU H,ZHANG X W,TU L P.A modified particle swarm optimization using adaptive strategy[J].Expert Systems with Applications.2020,152:113359.

[29] 李二超,高振磊.改进粒子速度和位置更新公式的粒子群优化算法[J].南京师大学报(自然科学版),2022,45(1):120-123.

[30] WANG L,YU Y,LIU W,et al.Three-heartbeat multilead ECG recognition method for arrhythmia classification[J].IEEE Access,2022,10:44057-44058.

[31] SHI H T,WANG H R,HUANG Y X,et al.A hierarchical method based on weighted extreme gradient boosting in ECG heartbeat classification [J].Computer Methods and Programs in Biomedicine,2019,171:6-9.