Department of Computer Science, Electrical and Space Engineering, Luleå University of Technology, Luleå, Sweden.
Biomed Phys Eng Express. 2020 Feb 18;6(2):025010. doi: 10.1088/2057-1976/ab6e1e.
The 2017 PhysioNet/CinC Challenge focused on automatic classification of atrial fibrillation (AF) in short ECGs. This study aimed to evaluate the use of the data and results from the challenge for detection of AF in longer ECGs, taken from three other PhysioNet datasets.
The used data-driven models were based on features extracted from ECG recordings, calculated according to three solutions from the challenge. A Random Forest classifier was trained with the data from the challenge. The performance was evaluated on all non-overlapping 30 s segments in all recordings from three MIT-BIH datasets. Fifty-six models were trained using different feature sets, both before and after applying three feature reduction techniques.
Based on rhythm annotations, the AF proportion was 0.00 in the MIT-BIH Normal Sinus Rhythm (N = 46083 segments), 0.10 in the MIT-BIH Arrhythmia (N = 2880), and 0.41 in the MIT-BIH Atrial Fibrillation (N = 28104) dataset. For the best performing model, the corresponding detected proportions of AF were 0.00, 0.11 and 0.36 using all features, and 0.01, 0.10 and 0.38 when using the 15 best performing features.
The results obtained on the MIT-BIH datasets indicate that the training data and solutions from the 2017 Physionet/Cinc Challenge can be useful tools for developing robust AF detectors also in longer ECG recordings, even when using a low number of carefully selected features. The use of feature selection allows significantly reducing the number of features while preserving the classification performance, which can be important when building low-complexity AF classifiers on ECG devices with constrained computational and energy resources.
2017 年 PhysioNet/CinC 挑战赛专注于短 ECG 中房颤（AF）的自动分类。本研究旨在评估挑战赛的数据和结果在更长 ECG 中检测 AF 的使用情况，这些 ECG 来自另外三个 PhysioNet 数据集。
使用的数据驱动模型基于从 ECG 记录中提取的特征，根据挑战赛的三种解决方案进行计算。使用挑战赛的数据训练随机森林分类器。在三个 MIT-BIH 数据集的所有记录中的所有非重叠 30 秒段上评估性能。使用不同的特征集在 56 个模型上进行训练，包括在应用三种特征降维技术之前和之后。
根据节律注释，MIT-BIH 正常窦性节律（N = 46083 个段）中的 AF 比例为 0.00，MIT-BIH 心律失常（N = 2880）中的 AF 比例为 0.10，MIT-BIH 心房颤动（N = 28104）中的 AF 比例为 0.41。对于表现最佳的模型，使用所有特征时，相应检测到的 AF 比例分别为 0.00、0.11 和 0.36，使用 15 个表现最佳的特征时，相应检测到的 AF 比例分别为 0.01、0.10 和 0.38。
在 MIT-BIH 数据集上获得的结果表明，2017 年 Physionet/CinC 挑战赛的训练数据和解决方案可作为开发更强大的 AF 检测器的有用工具，即使在使用少量精心挑选的特征时，也可用于更长的 ECG 记录。特征选择的使用允许显著减少特征数量，同时保持分类性能，这在使用计算和能量资源有限的 ECG 设备构建低复杂度 AF 分类器时非常重要。
