AF Classification from a Short Single Lead ECG Recording: the PhysioNet/Computing in Cardiology Challenge 2017.
AF Classification from a Short Single Lead ECG Recording: the PhysioNet/Computing in Cardiology Challenge 2017.
复制标题
DOI：
10.22489/cinc.2017.065-469
复制
发表时间：
2017-09
期刊：
影响因子：
--
通讯作者：
Mark RG
中科院分区：
文献类型：
--
作者：
Clifford GD;Liu C;Moody B;Lehman LH;Silva I;Li Q;Johnson AE;Mark RG
2017年PhysioNet/Computing in Cardiology（CinC）挑战赛的重点是在患者进行的短期（9-61秒）ECG记录中区分AF与噪声、正常或其他节律。总共使用了12，186个ECG：公共训练集中8，528个，私人隐藏测试集中3，658个。由于专家之间的高度分歧的显着部分的专家标签，我们实施了一个中期竞争的自举方法，专家重新标记的数据，勒韦林的最佳表现参赛者的算法，以确定有争议的标签。共有75个独立团队使用各种传统和新颖的方法参加了挑战赛，从随机森林到应用于光谱域原始数据的深度学习方法。四支球队以同样高的F1得分（所有类别的平均值）0.83赢得了挑战赛，尽管前11名算法的得分在2%以内。使用LASSO识别的45种算法的组合实现了0.87的F1，表明投票方法可以提高性能。
The PhysioNet/Computing in Cardiology (CinC) Challenge 2017 focused on differentiating AF from noise, normal or other rhythms in short term (from 9–61 s) ECG recordings performed by patients. A total of 12,186 ECGs were used: 8,528 in the public training set and 3,658 in the private hidden test set. Due to the high degree of inter-expert disagreement between a significant fraction of the expert labels we implemented a mid-competition bootstrap approach to expert relabeling of the data, levering the best performing Challenge entrants’ algorithms to identify contentious labels. A total of 75 independent teams entered the Challenge using a variety of traditional and novel methods, ranging from random forests to a deep learning approach applied to the raw data in the spectral domain. Four teams won the Challenge with an equal high F1 score (averaged across all classes) of 0.83, although the top 11 algorithms scored within 2% of this. A combination of 45 algorithms identified using LASSO achieved an F1 of 0.87, indicating that a voting approach can boost performance.