Table 3 Best accuracy for each ML model—with expert’s opinion as input. Standard deviation (STD) is included in parentheses.

From: Classification models for assessing coronary artery disease instances using clinical and biometric data: an explainable man-in-the-loop approach

 

SVM

DT

KNN

ADA

RF

GA

82.66% (3.80)

81.96% (4.95)

83.01% (6.34)

81.26% (4.13)

83.02% (4.27)

Bwd SFS

82.13% (4.15)

78.63% (6.34)

82.66% (6.87)

79.69% (4.74)

75.48% (5.13)

Fwd SFS

81.78% (5.28)

78.81% (5.80)

82.14% (5.65)

80.74% (5.15)

77.23% (3.96)

All features

80.73% (5.09)

71.10% (5.30)

79.34% (4.01)

77.60% (5.65)

77.23% (5.96)

  1. Significant values are in bold.
Back to article page