Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School, Braunschweig, 38106 Lower Saxony, Germany.
Sensors (Basel). 2021 May 19;21(10):3542. doi: 10.3390/s21103542.
Early detection of atrial fibrillation from electrocardiography (ECG) plays a vital role in the timely prevention and diagnosis of cardiovascular diseases. Various algorithms have been proposed; however, they are lacking in considering varied-length signals, morphological transitions, and abnormalities over long-term recordings. We propose dynamic symbolic assignment (DSA) to differentiate a normal sinus rhythm (SR) from paroxysmal atrial fibrillation (PAF). We use ECG signals and their interbeat (RR) intervals from two public databases namely, AF Prediction Challenge Database (AFPDB) and AF Termination Challenge Database (AFTDB). We transform RR intervals into a symbolic representation and compute co-occurrence matrices. The DSA feature is extracted using varied symbol-length V, word-size W, and applied to five machine learning algorithms for classification. We test five hypotheses: (i) DSA captures the dynamics of the series, (ii) DSA is a reliable technique for various databases, (iii) optimal parameters improve DSA's performance, (iv) DSA is consistent for variable signal lengths, and (v) DSA supports cross-data analysis. Our method captures the transition patterns of the RR intervals. The DSA feature exhibit a statistically significant difference in SR and PAF conditions ( < 0.005). The DSA feature with W=3 and V=3 yield maximum performance. In terms of F-measure (F), rotation forest and ensemble learning classifier are the most accurate for AFPDB (F = 94.6%) and AFTDB (F = 99.8%). Our method is effective for short-length signals and supports cross-data analysis. The DSA is capable of capturing the dynamics of varied-lengths ECG signals. Particularly, the optimal parameters-based DSA feature and ensemble learning could help to detect PAF in long-term ECG signals. Our method maps time series into a symbolic representation and identifies abnormalities in noisy, varied-length, and pathological ECG signals.
从心电图 (ECG) 中早期检测心房颤动对于及时预防和诊断心血管疾病至关重要。已经提出了各种算法；然而，它们缺乏对长短不一的信号、形态转变和长期记录中的异常的考虑。我们提出了动态符号分配 (DSA) 来区分正常窦性节律 (SR) 和阵发性心房颤动 (PAF)。我们使用来自两个公共数据库的 ECG 信号及其心拍间 (RR) 间隔，即心房颤动预测挑战数据库 (AFPDB) 和心房颤动终止挑战数据库 (AFTDB)。我们将 RR 间隔转换为符号表示，并计算共现矩阵。使用不同的符号长度 V、字长 W 提取 DSA 特征，并应用于五种机器学习算法进行分类。我们测试了五个假设：(i) DSA 捕获了序列的动态，(ii) DSA 是各种数据库的可靠技术，(iii) 最佳参数提高了 DSA 的性能，(iv) DSA 对可变信号长度是一致的，(v) DSA 支持跨数据分析。我们的方法捕获了 RR 间隔的过渡模式。在 SR 和 PAF 条件下，DSA 特征表现出统计学上的显著差异（<0.005）。在 W=3 和 V=3 的 DSA 特征下，性能达到最大值。就 F 度量 (F) 而言，旋转森林和集成学习分类器在 AFPDB（F=94.6%）和 AFTDB（F=99.8%）中是最准确的。我们的方法对短长度信号有效，并支持跨数据分析。DSA 能够捕获长短不一的 ECG 信号的动态。特别是，基于最佳参数的 DSA 特征和集成学习可以帮助检测长期 ECG 信号中的 PAF。我们的方法将时间序列映射到符号表示中，并识别出噪声、长短不一和病理 ECG 信号中的异常。
