Skip to main content

Table 2 Comparison of the efficacy of AI models

From: A validation of an entropy-based artificial intelligence for ultrasound data in breast tumors

Model

AUC

(95%CI)

Sensitivity

(%)

Specificity

(%)

Accuracy

(%)

P value

L9

0.849

(0.735–0.962)

76.9

93.2

87.1

0.4185#

L14

0.784

(0.655–0.913)

65.4

90.9

81.4

 

L7

0.887

(0.820–0.953)

71.8

93.4

85.0

0.0383*

L13

0.920

(0.851–0.989)

89.7

91.8

91.0

 
  1. Note: AUC: area under the curve; 95% CI: 95% confidence interval; L9: L9 linear array probe, frequency range: 2.5-9.0 MHz, central frequency 6.5 MHz; L14: L14 linear array probe, frequency range: 3.0-14.0 MHz, central frequency 9 MHz; L7: L7 linear array probe, frequency range: 3-7 MHz, central frequency 4.0 MHz; L13: L13 linear array probe, frequency range: 3.6-13.5 MHz, central frequency 8 MHz; P value #: L9 vs. L14; *: L7 vs. L13
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us