基于相空间形状分析预测房颤终止

Predicting the atrial fibrillation termination based on the shape analysis of the reconstructed state space

识别和描述房颤有可能自发终止还是持续,不仅可以更好地了解心律不齐发作和终止的机制,还可以更有效地治疗持续房颤。本文从非线性角度提取房颤信号特征并预测其能否自发终止。先重建心电信号的相空间,获取相空间中指定庞加莱截面上的点,然后基于形状分析提取刻画庞加莱面上相似点对相对数量的参数ρ,最后基于ρ来分类非终止房颤和可终止房颤。实验研究了一个由Holter心电信号组成的包括训练集和测试集的房颤数据库,结果表明:本文提出的特征参数ρ可正确分类90%的测试集。可见,该方法能从Holter心电信号有效地预测房颤的自发终止。

Recognizing and characterizing whether the atrial fibrillation （AF） is likely to terminate spontaneously or be sustained leads to not only the better understanding of onset and termination mechanisms of the arrhythmia but also the improved treatment of the sustained AF. In this paper, a novel methodology is proposed to characterize the AF from the nonlinear point of view to predict its spontaneous termination. The state space of the electrocardiography （ECG） signal is firstly reconstructed and points on the given Poincare surface are obtained. Then a regularity index, p is calculated to characterize the relative number of similar pairs of points on the Poincare surface based on the shape analysis. Finally, the non-terminating and the terminating AF are classified based on p. Here an AF database which includes a training set with known termination properties and a testing set of Holter ECG recordings is studied in the experiment. Results show that with the proposed feature, 90% of the testing set is correctly classified. It demonstrates that the algorithm has the ability to predict the spontaneous termination of the AF from Holter ECG recordings effectively.