期刊
AUSTRALASIAN PHYSICAL & ENGINEERING SCIENCES IN MEDICINE
卷 40, 期 3, 页码 707-716出版社
SPRINGER
DOI: 10.1007/s13246-017-0554-2
关键词
Arrhythmia; Atrial fibrillation (AF); Grid map; Probability density distribution (PDD); Delta RR intervals (Delta RR); Atrial fibrillation database
资金
- State Key Laboratory of Space Medicine Fundamentals and Application, China Astronaut Research and Training Center [SMFA15B06, SMFA15A01]
- China National Natural Science Fund [81471743, 81601561, 61401417]
Atrial fibrillation (AF) monitoring and diagnosis require automatic AF detection methods. In this paper, a novel image-based AF detection method was proposed. The map was constructed by plotting changes of RR intervals (a-(RR)-R-3) into grid panes. First, the map was divided into grid panes with 20 ms fixed resolution in y-axes and 15-60 s step length in x-axes. Next, the blank pane ratio (BPR), the entropy and the probability density distribution were processed using linear support-vector machine (LSVM) to classify AF and non-AF episodes. The performance was evaluated based on four public physiological databases. The Cohen's Kappa coefficients were 0.87, 0.91 and 0.64 at 50 s step length for the long-term AF database, the MIT-BIH AF database and the MIT-BIH arrhythmia database, respectively. Best results were achieved as follows: (1) an accuracy of 93.7%, a sensitivity of 95.1%, a specificity of 92.0% and a positive predictive value (PPV) of 93.5% were obtained for the long-term AF database at 60 s step length. (2) An accuracy of 95.9%, a sensitivity of 95.3%, a specificity of 96.3% and a PPV of 94.1% were obtained for the MIT-BIH AF database at 40 s step length. (3) An accuracy of 90.6%, a sensitivity of 94.5%, a specificity of 90.0% and a PPV of 55.0% were achieved for the MIT-BIH arrhythmia database at 60 s step length. (4) Both accuracy and specificity were 96.0% for the MIT-BIH normal sinus rhythm database at 40 s step length. In conclusion, the intuitive grid map of delta RR intervals offers a new approach to achieving comparable performance with previously published AF detection methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据