Skip to main content

Table 3 Comparative results of different methods on the whole ABIDE dataset with 871 subjects

From: A heterogeneous graph convolutional attention network method for classification of autism spectrum disorder

Model

ACC (%)

SEN (%)

SPE (%)

AUC

Time (s)

MLP

78.1 ± 4.7

77.2 ± 4.9

79.8 ± 4.8

83.1 ± 3.1

156

GCN

79.5 ± 3.3

78.3 ± 3.5

81.2 ± 3.6

84.8 ± 2.7

186

HAN

64.4 ± 2.9

38.7 ± 16.5

85.5 ± 12.4

64.4 ± 5.2

1556

HCAN

82.1 ± 3.3

76.7 ± 4.8

86.6 ± 3.6

84.6 ± 3.1

256

ASD-DiagNet

66.4 ± 3.9

55.60 ± 11.5

75.6 ± 8.9

73.0 ± 5.3

1924

  1. The highest average values of ACC, SEN, AUC, and SPE are indicated in bold
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us