Quality estimation of the electrocardiogram using cross-correlation among leads

Table 1 Performance comparison of ECG signal quality algorithms

	E1	E2	E3
Physionet/CinC Challenge (accuracy scores)
Xia et al. [3]^a	0.932	0.914	0.845
Clifford et al. [4]	0.926	\(-\)	\(-\)
Tat et al. [7]	0.920	\(-\)	\(-\)
Hayn et al. [8, 17]	0.916	0.834	0.873
Kalkstein et al. [5]	0.912	\(-\)	\(-\)
Jekova et al. [9, 18]	0.908	\(-\)	\(-\)
Zausender et al. [6]	0.904	\(-\)	\(-\)
Noponen et al. [10]	0.900	\(-\)	\(-\)
Moody [11]	0.896	0.896	0.802
Johannesen et al. [13, 20]	0.880	0.880	0.791
Langley et al. [12]	0.868	0.868	0.814
Chudacek et al. [14]	0.828	0.833	0.872
Other studies (accuracy score in the test set^b)
Clifford et al. [16]	0.970
Xia et al. [1]^c	0.951
Langley et al. [19]	0.914

Physionet/CinC Challenge was divided into three events: event 1 (E1), where participants were not required to submit their code; event 2 (E2), where participant were required to submit the code; and event 3 (E3), where the open source code of E2 was tested on a data set not available for participants. Accuracy scores for both E1 and E2 are calculated on the Dataset B by the Challenge organizers (see "Methods" section), while for E3 the accuracy was calculated on Dataset C.
^aThe score reported in [3] is different from the official entry [2].
^bThe test set is different from the Physionet/Cinc Challenge set.
^cThe reported accuracy was calculated for the training set.

ISSN: 1475-925X