Table 4 Main Performance Results without Interferant Set (Hidden Size = 5000).

From: Linking sequence restoration capability of shuffled coronary angiography to coronary artery disease diagnosis

 

SYNTAX >  = 23

 

Group1

Group2

Group3

AUC-median–%(95% CI)

83.909 (70.512—91.416)

88.63 (76.423—99.238)

79.035 (67.228—89.551)

Sensitivity – %(95%CI)

99.1 (75.3 – 100.0)

100.0 (100.0—100.0)

99.8 (85.394 – 100.0)

Specificity – %(95%CI)

69.25 (47.375—90.825)

86.5 (74.0—97.625)

65.406 (47.759—82.653)

Positive predictive value – %(95%CI)

74.119 (64.988—89.505)

89.898 (79.9—97.12)

73.869 (65.291—83.442)

Negative predictive value – %(95%CI)

99.5 (74.5—100.0)

99.9 (99.9 – 100.0)

100.0 (83.421—100.0)

 

Group4

Group5

 

AUC-median–%(95% CI)

71.118 (55.832—82.722)

79.817 (67.703—90.652)

 

Sensitivity – %(95%CI)

56.567 (40.2 – 100.0)

77.018 (58.924—91.576)

 

Specificity – %(95%CI)

93.008 (32.933—100.0)

88.327 (73.729—97.859)

 

Positive predictive value – %(95%CI)

89.574 (59.932—100.0)

86.003 (74.008—96.801)

 

Negative predictive value – %(95%CI)

68.455 (60.717—100.0)

78.424 (68.285—91.009)

 

5 Groups AUC Mean

80.502 (73.020–90.716)

  1. Bootstrapping is used to estimate 95% confidence intervals (CI) for the performance metrics of our classification results (i.e., AUC, sensitivity, specificity). We apply n-out of-n bootstrap with replacement from our dataset. For each bootstrap sample, we calculate and reserved the performance metrics for that bootstrap sample. The bootstrap sampling is repeated for 2000 times. We then estimate the 95% CI by using the 2.5 and 97.5 percentiles of the empirical distribution of corresponding metrics. All the results retain 3 decimal places, unless the last decimal is 0.
  2. AUC = Area Under the Curve. SYNTAX = Synergy between Percutaneous Coronary Intervention (PCI) with Taxus and Cardiac Surgery.
Back to article page