Beat by Beat: Classifying Cardiac Arrhythmias with Recurrent Neural Networks

被引:55
作者
Schwab, Patrick [1 ]
Scebba, Gaetano C. [1 ]
Zhang, Jia [1 ]
Delai, Marco [1 ]
Karlen, Walter [1 ]
机构
[1] Swiss Fed Inst Technol, Dept Hlth Sci & Technol, Mobile Hlth Syst Lab, Zurich, Switzerland
来源
2017 COMPUTING IN CARDIOLOGY (CINC) | 2017年 / 44卷
基金
瑞士国家科学基金会;
关键词
ATRIAL-FIBRILLATION;
D O I
10.22489/CinC.2017.363-223
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
With tens of thousands of electrocardiogram (ECG) records processed by mobile cardiac event recorders every day, heart rhythm classification algorithms are an important tool for the continuous monitoring of patients at risk. We utilise an annotated dataset of 12,186 single-lead ECG recordings to build a diverse ensemble of recurrent neural networks (RNNs) that is able to distinguish between normal sinus rhythms, atrial fibrillation, other types of arrhythmia and signals that are too noisy to interpret. In order to ease learning over the temporal dimension, we introduce a novel task formulation that harnesses the natural segmentation of ECG signals into heartbeats to drastically reduce the number of time steps per sequence. Additionally, we extend our RNNs with an attention mechanism that enables us to reason about which heartbeats our RNNs focus on to make their decisions. Through the use of attention, our model maintains a high degree of interpretability, while also achieving state-of-the-art classification performance with an average F1 score of 0.79 on an unseen test set (n=3,658).
引用
收藏
页数:4
相关论文
共 25 条
[1]  
Alcaraz R., 2006, Comput. Cardiol, V2006, P597
[2]  
[Anonymous], 2017, ARXIV
[3]  
[Anonymous], 2013, P 12 PYTH SCI C
[4]  
[Anonymous], NEURAL INFORM PROCES
[5]  
[Anonymous], 2017, ARXIV170702485
[6]  
[Anonymous], 2015, 3 INT C LEARN REPR I
[7]   Atrial fibrillation: Profile and burden of an evolving epidemic in the 21st century [J].
Ball, Jocasta ;
Carrington, Melinda J. ;
McMurray, John J. V. ;
Stewart, Simon .
INTERNATIONAL JOURNAL OF CARDIOLOGY, 2013, 167 (05) :1807-1824
[8]   Unintended Consequences of Machine Learning in Medicine [J].
Cabitza, Federico ;
Rasoini, Raffaele ;
Gensini, Gian Franco .
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2017, 318 (06) :517-518
[9]  
Camm AJ, 2010, EUR HEART J, V31, P2369, DOI [10.1093/eurheartj/ehq278, 10.1093/europace/euq350]
[10]  
Clifford G, 2017, COMPUTING CARDIOLOGY