Skip to main content

Table 4 Parameters of diagnostic performance

From: Development and validation of a multi-modal ultrasomics model to predict response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer

Model

 

BUS

CEUS

Combined_1

Combined_2

Clinical

Training cohort

AUC

(95%CI)

0.751

(0.640–0.862)

0.714

(0.598–0.831)

0.833

(0.740–0.927)

0.844

(0.757–0.932)

0.680

(0.569–0.792)

Accuracy (%)

71.6

67.6

78.4

79.7

67.7

Sensitivity (%)

73.0

70.3

67.6

75.7

78.4

Specificity (%)

70.3

64.9

89.2

83.8

56.8

PPV (%)

71.1

66.7

86.2

82.4

64.4

NPV (%)

72.2

68.6

73.3

77.5

72.4

Validation cohort

AUC

(95%CI)

0.675

(0.481–0.868)

0.821

(0.660–0.983)

0.829

(0.673–0.985)

0.893

(0.780-1.000)

0.690

(0.509–0.872)

Accuracy (%)

68.8

81.2

78.1

84.4

71.9

Sensitivity (%)

57.1

64.3

92.9

78.6

78.6

Specificity (%)

77.8

94.4

66.7

88.9

66.7

PPV (%)

66.7

90.0

68.4

84.6

64.7

NPV (%)

70.0

77.3

92.3

84.2

80.0

  1. BUS: B-mode ultrasound; CEUS: contrast-enhanced ultrasound; Combined_1: the integration of BUS and CEUS; Combined_2: the integration of BUS, CEUS, and deep learning; AUC: area under the curve; 95% CI: 95% confidence intervals; PPV: positive predictive value; NPV: negative predictive value. Data in brackets are the 95% confidence intervals