Skip to main content

Table 2 Performance of screening mammography compared between radiologists and standalone AI

From: Screening mammography performance according to breast density: a comparison between radiologists versus standalone intelligence detection

Outcome

Radiologists’

BI-RADS category (0, 3, 4, 5)

Standalone AI

(Cutoff 10%)

P value

Estimate

95% CI

Estimate

95% CI

CDR, per 1000 examinations

1.1

0.9–1.4

1.1

0.9–1.3

0.516

Sensitivity, %

69.9

61.7–77.3

67.1

58.8–74.8

0.516

Specificity, %

77.6

61.7–77.9

93.0

92.9–93.2

< 0.001

PPV, %

0.5

0.4–0.6

1.5

1.2–1.9

< 0.001

Recall rate, %

22.5

22.2–22.7

7.1

6.9–7.2

< 0.001

AUC

0.74

0.70–0.78

0.80

0.76–0.84

0.004

  1. AI, artificial intelligence; AUC, area under the receiver operating characteristic curve; BI-RADS, Breast Imaging Reporting and Data System; CDR, cancer detection rate; CI, confidence interval; PPV, positive predictive value