Skip to main content

Table 5 Subgroup analysis of MRI-based prediction model

From: Prediction model based on MRI morphological features for distinguishing benign and malignant thyroid nodules

Subgroup

N (%)

Sensitivity (%)

Specificity (%)

Accuracy (%)

PPV (%)

NPV (%)

Number

      

 Unifocal nodules subgroup

252(30.5)

93.2

81.1

88.9

89.9

86.9

 Multifocal nodules subgroup

573(69.5)

96.1

95.7

95.8

89.2

98.5

Hashimoto′s thyroiditis

      

 Hashimoto′s thyroiditis subgroup

137(16.6)

94.6

96.8

95.6

97.2

93.8

 Non-Hashimoto′s thyroiditis subgroup

688(83.4)

94.7

92.6

93.3

87.5

96.9

Size

      

 Small nodules subgroup (0.5-1 cm)

272 (33.0)

96.5

87.0

91.9

88.9

95.8

 Medium nodules subgroup (1-4 cm)

452 (54.8)

97.4

95.3

96.0

91.6

98.6

 Large nodules subgroup (≥4 cm)

101 (12.2)

60.0

95.1

88.1

75.0

90.6

  1. Abbreviation: N, number; PPV, positive predictive value; NPV, negative predictive value; AUC, area under the curve