Novel Density Poincaré Plot Based Machine Learning Method to Detect Atrial Fibrillation From Premature Atrial/Ventricular Contractions.
Novel Density Poincaré Plot Based Machine Learning Method to Detect Atrial Fibrillation From Premature Atrial/Ventricular Contractions.
复制标题
一种基于密度Poincaré图的机器学习方法，用于从房/室性早搏中检测房颤。
DOI：
10.1109/tbme.2020.3004310
复制
发表时间：
2021-03
期刊：
影响因子：
--
通讯作者：
Chon KH
中科院分区：
文献类型：
--
作者：
Bashar SK;Han D;Zieneddin F;Ding E;Fitzgibbons TP;Walkey AJ;McManus DD;Javidi B;Chon KH
从房性早搏（PAC）和室性早搏（PVC）中检测心房颤动（AF）是困难的，因为频繁发生的这些异位搏动可以模仿AF的典型不规则模式。在本文中，我们提出了一种新的基于密度Poincaré图的机器学习方法，使用心电图（ECG）记录从PAC/PVC中检测AF。首先，我们提出了这种新的密度庞加莱图的生成，这是来自心率（DHR）的差异，并提供重叠的相空间轨迹信息的DHR。其次，从这个密度Poincaré图，几个图像处理域为基础的方法，包括统计中心矩，模板相关，Zernike矩，离散小波变换和Hough变换特征被用来提取合适的功能。随后，无限的潜在特征选择算法实现的功能排名。最后，使用K-最近邻、支持向量机（SVM）和随机森林（RF）分类器对AF与PAC/PVC进行分类。我们的方法是使用包含10名AF和10名PAC/PVC受试者的重症监护医学信息市场（MIMIC）III数据库的子集开发和验证的。在分段10倍交叉验证期间，SVM利用提取的特征实现了最佳性能，具有98.99%的灵敏度，95.18%的特异性和97.45%的准确性。在受试者方面，RF达到了91.93%的最高准确度。此外，我们进一步验证了所提出的方法使用其他两个数据库：可穿戴臂带ECG数据和Physionet AFPDB。两个数据库均获得了100%的PAC检测准确度，无需任何进一步的培训。我们提出的密度庞加莱图为基础的方法表现出上级性能与现有的四种算法相比，从而显示出提取的图像域为基础的功能的功效。从重症监护室的ECG到可穿戴臂带ECG，所提出的方法被示出以高精度区分PAC/PVC与AF。
Detection of Atrial fibrillation (AF) from premature atrial contraction (PAC) and premature ventricular contraction (PVC) is difficult as frequent occurrences of these ectopic beats can mimic the typical irregular patterns of AF. In this paper, we present a novel density Poincaré plot-based machine learning method to detect AF from PAC/PVCs using electrocardiogram (ECG) recordings. First, we propose the generation of this new density Poincaré plot which is derived from the difference of the heart rate (DHR) and provides the overlapping phase-space trajectory information of the DHR. Next, from this density Poincaré plot, several image processing domain-based approaches including statistical central moments, template correlation, Zernike moment, discrete wavelet transform and Hough transform features are used to extract suitable features. Subsequently, the infinite latent feature selection algorithm is implemented to rank the features. Finally, classification of AF vs. PAC/PVC is performed using K-Nearest Neighbor, Support vector machine (SVM) and Random Forest (RF) classifiers. Our method is developed and validated using a subset of Medical Information Mart for Intensive Care (MIMIC) III database containing 10 AF and 10 PAC/PVC subjects. During the segment-wise 10-fold cross-validation, SVM achieved the best performance with 98.99% sensitivity, 95.18% specificity and 97.45% accuracy with the extracted features. In subject-wise scenario, RF achieved the highest accuracy of 91.93%. Moreover, we further validated the proposed method using two other databases: wearable armband ECG data and the Physionet AFPDB. 100% PAC detection accuracy was obtained for both databases without any further training. Our proposed density Poincaré plot-based method showed superior performance when compared with four existing algorithms; thus showing the efficacy of the extracted image domain based features. From intensive care unit’s ECG to wearable armband ECGs, the proposed method is shown to discriminate PAC/PVCs from AF with high accuracy.