Skip to main content

Table 3 Mean Accuracy, Sensitivity, Specificity and Area under ROC curve in the 3-CV sets for the ANN architectures obtained by the PDM-ANN and the GA-ANN (T = Inf and T = 30)

From: A multifactorial analysis of obesity as CVD risk factor: Use of neural network based methods in a nutrigenetics context

Measurement ANN architecture Mean Value in 3-CV Training Sets Mean Value in 3-CV Testing Sets
  PDM-ANN
(32 factors)
95.56 60.22
Accuracy (%) GA-ANN, T = Inf
(32 factors)
97.67 60.69
  GA-ANN, T = 30
(25 factors)
97.10 61.46
  PDM-ANN
(32 factors)
98.14 69.15
Sensitivity (%) GA-ANN, T = Inf
(32 factors)
99.39 70.79
  GA-ANN, T = 30
(25 factors)
98.90 69.80
  PDM-ANN
(32 factors)
91.15 46.08
Specificity (%) GA-ANN, T = Inf
(32 factors)
94.73 44.62
  GA-ANN, T = 30
(25 factors)
94.54 48.63
  PDM-ANN
(32 factors)
0.941 0.580
Area under ROC curve GA-ANN, T = Inf
(32 factors)
0.969 0.574
  GA-ANN, T = 30
(25 factors)
0.964 0.608