Skip to main content
. 2018 Jul 17;9:929. doi: 10.3389/fphys.2018.00929

Table 7.

ROC analysis of the AF complexity features and CA outcome.

AUC [%] Sensitivity [%] Specificity [%]
NDI [a.u] 69 70 67
AF duration [months] 70 55 87
LA area [cm2] 51 65 53
AV1 [mV] 51 84 33
CLV1 [ms] 52 37 75
NMSE3 [%] 56 32 85
WNMSEBSPM [%] 57 95 26
ABSPM [mV] 67 85 40
NDIECG [a.u] 56 37 81
WNMSEECG [%] 53 63 49
AECG [mV] 51 84 33
NDIOACG [a.u] 57 37 88
WNMSEOACG [%] 52 63 52
AOACG [mV] 50 98 24
NDIECG15 [a.u] 58 47 85
WNMSEECG15 [%] 51 95 26
AECG15 [mV] 54 84 33

Assessment of the ability of the AF organization descriptors to predict AF termination by CA. Sensitivity and specificity indicate the rate of detection of successful and failed ablation procedures, respectively. Results for the parameters with the highest classification performance (AUC≥70%) are highlighted in boldface. AUC, area under curve; a.u., arbitrary units.