Table 4 Best accuracy for each ML model—without expert’s opinion as input. 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

78.12% (4.24)

73.04% (2.49)

76.37% (3.10)

76.54% (3.74)

77.59% (3.13)

Bwd SFS

77.77% (3.61)

76.01% (4.32)

77.95% (3.38)

75.49% (4.12)

74.09% (3.72)

Fwd SFS

78.29% (3.86)

78.29% (4.32)

75.84% (4.44)

75.49% (3.82)

76.54% (2.62)

All features

74.79% (2.19)

66.37% (5.73)

70.76% (3.45)

74.09% (4.02)

72.33% (6.15)

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