Cutoff point for predicted masking risk (%)^{a}

Frequency above cutoff point (%)^{b}

Discovery rates for tumors not seen on mammography (%)


Clinical model^{c}

Boosting PMD model^{d}

Observed PMD model^{e}


5

47.5

81.8

80.9

78.9

10

26.4

54.5

57.7

55.6

12

20.0

44.8

47.4

48.7

15

13.6

32.9

35.1

39.7

20

7.5

16.2

21.0

25.4

 All measurements were obtained by 3fold crossvalidation with 100 repetitions

BMI body mass index, HRT hormone replacement therapy, PMD percentage mammographic density

^{a}Patients were classified into a “highrisk” group if the prediction model assigned a masking risk above the cutoff point. Discovery rates are defined as the proportion of masked tumors in the “highrisk” group

^{b}Proportion of “high risk” classified patients in the total study population, using boostingbased prediction model

^{c}Logistic regression model with the clinical predictors age, BMI, previous breast surgery, menopausal and HRT status, and imaging technique

^{d}Logistic regression model with the same clinical predictors and additionally PMD predicted by a boosting regression model beforehand

^{e}Logistic regression model with the clinical predictors and the observed PMD