Table 4 Comparison of the accuracy for challenging-to-distinguish subjects with prior works which have conducted subject-specific experiments on the CHB-MIT dataset.

From: Synchronization-based graph spatio-temporal attention network for seizure prediction

Study

Chb2

Chb5

Chb6

Chb9

Chb10

Chb14

Chb16

Chb18

Chb21

Yuan Zhang17

92

89

86

90

96

84

86

–

80

Qizhong Zhang32

82.5

77.5

87.5

90

77.5

–

–

–

–

Xinwu Yang35

89.7

92.9

-

91

77.7

73.7

–

96

88.3

IMENE JEMAL52

95.7

85.2

86.2

88.2

90.9

75.2

86.2

-

89.3

Hong Ji36

94.15

90.88

-

-

78.11

77.11

-

90.4

89.03

Ding, Xin53

81.94

82.25

81.38

91.29

77.7

83.01

76.49

90.26

91.6

SGSTAN

97.63

96.93

95.8

97.69

98.99

98.85

98.44

98.09

95.93