School of Electrical and Information Engineering, University of Sydney, Sydney, Australia. Charles Perkins Centre, University of Sydney, Sydney, Australia. School of Electrical and Information Engineering, University of Sydney, NSW 2006, Sydney, Australia.
Physiol Meas. 2018 Jun 20;39(6):064003. doi: 10.1088/1361-6579/aac76c.
We present a method for automatic processing of single-lead electrocardiogram (ECG) with duration of up to 60 s for the detection of atrial fibrillation (AF). The method categorises an ECG recording into one of four categories: normal, AF, other and noisy rhythm. For training the classification model, 8528 scored ECG signals were used; for independent performance assessment, 3658 scored ECG signals.
Our method was based on features derived from RR interbeat intervals. The features included time domain, frequency domain and distribution features. We assessed the performance of three different classifiers (linear and quadratic discriminant analysis, and quadratic neural network (QNN)) on the training set using 100-fold cross-validation. The QNN was selected as the highest performing classifier, and a further performance assessment on the test data made.
On the test set, our method achieved an F1 score for the normal, AF, other and noisy classes of 0.90, 0.75, 0.68 and 0.32, respectively. The overall F1 score was 0.78.
The computational cost of our algorithm is low as all features are derived from RR intervals and are processed by a single hidden layer neural network. This makes it potentially suitable for low-power devices.
我们提出了一种用于自动处理长达 60 秒的单导联心电图（ECG）的方法，用于检测心房颤动（AF）。该方法将心电图记录分为四类：正常、AF、其他和噪声节律。为了训练分类模型，使用了 8528 个有评分的 ECG 信号；为了进行独立性能评估，使用了 3658 个有评分的 ECG 信号。
我们的方法基于从 RR 间期中提取的特征。这些特征包括时域、频域和分布特征。我们使用 100 倍交叉验证在训练集上评估了三种不同分类器（线性和二次判别分析、二次神经网络（QNN））的性能。选择 QNN 作为性能最高的分类器，并在测试数据上进行了进一步的性能评估。
在测试集上，我们的方法对正常、AF、其他和噪声类的 F1 得分分别为 0.90、0.75、0.68 和 0.32，整体 F1 得分为 0.78。
我们算法的计算成本低，因为所有特征均来自 RR 间隔，并由单个隐藏层神经网络处理。这使其可能适用于低功耗设备。
