Skip to main content

Table 3 Ability of trained classifier to distinguish between BRCA1/2 mutation carriers and non-carriers in testing dataset

From: Relationships between computer-extracted mammographic texture pattern features and BRCA1/2mutation status: a cross-sectional study

Training dataset* Testing dataset Testing dataset results
Description Number of non-carriers Number of carriers Odds ratio 95% CI P-value Odds ratio 95% CI P-value OR 95% CI P-value AUC SE
    Unadjusted Adjusted for age Adjusted for age and PMD   
Percent mammographic density (PMD) alone 30 30 1.022 (0.99, 1.06) 0.21 1.002 (0.96, 1.04) 0.96 N/A    0.59 0.07
Features alone1 30 30 2.00 3 (1.59, 2.51) 0.02 1.93 3 (1.53, 2.42) 0.03 1.93 3 (1.54, 2.43) 0.03 0.68 0.07
Features1 + PMD 30 30 2.10 3 (1.67, 2.65) 0.01 2.03 3 (1.62, 2.56) 0.03 N/A    0.72 0.07
  1. *Training dataset includes 70 non-carriers and 107 BRCA1/2 mutation carriers. 1Four features were selected by the trained classifier: MinCDF, Energy, AVE, and MaxF (COOC); percent mammographic density was not selected by the trained classifier but was forced into the models where noted. 2Odds ratios, per unit increase in percent mammographic density. 3Odds ratios, per one SD increase in probability score from trained classifier; SD from both models = 0.342. AUC, area under the curve; N/A, not applicable; PMD, percent mammographic density; SE, standard error. P-values <0.05 are shown in bold font.