Automation School, Beijing University of Posts and Telecommunications, Beijing, People's Republic of China.
Physiol Meas. 2018 Jun 25;39(6):064004. doi: 10.1088/1361-6579/aac7aa.
In this paper, a support vector machine (SVM) approach using statistical features, P wave absence, spectrum features, and length-adaptive entropy are presented to classify ECG rhythms as four types: normal rhythm, atrial fibrillation (AF), other rhythm, and too noisy to classify.
The proposed algorithm consisted of three steps: (1) signal pre-processing based on the wavelet method; (2) feature extraction, the extracted features including one power feature, two spectrum features, two entropy features, 17 RR interval-related features, and 11 P wave features; and (3) classification using the SVM classifier.
The algorithm was trained by 8528 single-lead ECG recordings lasting from 9 s to just over 60 s and then tested on a hidden test set consisting of 3658 recordings of similar lengths, which were all provided by the PhysioNet/Computing in Cardiology Challenge 2017. The scoring for this challenge used an F measure, and the final F score was defined as the average of F (the F score of normal rhythm), F (the F score of AF rhythm), and F (the F score of other rhythm). The results confirmed the high accuracy of our proposed method, which obtained 90.27%, 86.37%, and 75.08% for F , F , and F and the final F score of 84% on the training set. In the final test to assess the performance of all of the hidden data, the obtained F , F , F and the average F were 90.82%, 78.56%, 71.77% and 80%, respectively.
The proposed algorithm targets a large number of raw, short single ECG data rather than a small number of carefully selected, often clean ECG records, which have been studied in most of the previous literature. It breaks through the limitation in applicability and provides reliable AF detection from a short single-lead ECG.
本文提出了一种基于统计特征、P 波缺失、频谱特征和长度自适应熵的支持向量机（SVM）方法，用于将心电图节律分为正常节律、心房颤动（AF）、其他节律和分类噪声过大四种类型。
该算法包括三个步骤：（1）基于小波方法的信号预处理；（2）特征提取，提取的特征包括一个功率特征、两个频谱特征、两个熵特征、17 个 RR 间期相关特征和 11 个 P 波特征；（3）使用 SVM 分类器进行分类。
该算法通过 8528 条持续时间从 9 秒到 60 多秒的单导联心电图记录进行训练，然后在由 3658 条相似长度记录组成的隐藏测试集中进行测试，这些记录均由 PhysioNet/Computing in Cardiology Challenge 2017 提供。该挑战赛的评分使用 F 度量，最终 F 分数定义为 F（正常节律的 F 分数）、F（AF 节律的 F 分数）和 F（其他节律的 F 分数）的平均值。结果证实了我们提出的方法的高精度，在训练集上，F、F 和 F 的得分分别为 90.27%、86.37%和 75.08%，最终 F 分数为 84%。在最终测试中，评估所有隐藏数据的性能，获得的 F、F、F 和平均 F 分别为 90.82%、78.56%、71.77%和 80%。
该算法针对大量原始的、短的单导联心电图数据，而不是大多数以前文献中研究的少数精心挑选的、通常是干净的心电图记录。它突破了适用性的局限性，为从单导联心电图中可靠地检测 AF 提供了依据。
