Skip to main content

Table 5 Top five important risk factors in descending order for different ML algorithms based on the US population-based training samples in 10-fold internal statistical cross-validations

From: Machine learning techniques for personalized breast cancer risk prediction: comparison with the BCRAT and BOADICEA models

ML: random forest

ML: logistic regression

ML: adapt boosting

ML: linear model

ML: K-nearest neighbors

ML: linear discriminant

ML: quadratic discriminant

ML: MCMC GLMM

Number of biopsies

Number of first-degree relatives with breast cancer

Number of biopsies

Age

Number of biopsies

Age

Number of first-degree relatives with breast cancer

Number of biopsies

Age

Age

Age

Number of biopsies

Number of first-degree relatives with breast cancer

Number of biopsies

Number of biopsies

Age

Number of first-degree relatives with breast cancer

Number of biopsies

Number of first-degree relatives with breast cancer

Number of first-degree relatives with breast cancer

Age

Ethnicity

Age

Number of first-degree relatives with breast cancer

Age at menarche

Ethnicity

Age at menarche

Age at menarche

Ethnicity

Number of first-degree relatives with breast cancer

Ethnicity

Age at first live birth

Ethnicity

Age at first live birth

Ethnicity

Age at first live birth

Age at first live birth

Age at first live birth

Age at menarche

Age at menarche