Table 1.
Input variables.
Fig 1.
ROC curves for machine learning models with only BCRAT inputs and for the BCRAT.
These are the receiver operating characteristic (ROC) curves for the six machine learning models with only Breast Cancer Risk Prediction Tool (BCRAT) inputs and for the BCRAT. The six machine learning models include a logistic regression (LR), naive Bayes (NB), decision tree (DT), linear discriminant analysis (LDA), support vector machine (SVM), and neural network (NN). We report Delong 95% confidence intervals for each area under the receiver operating characteristic curve (AUC) value.
Table 2.
Statistics for machine learning models with only BCRAT inputs and for the BCRAT.
Table 3.
Comparisons between machine learning models with only BCRAT inputs and the BCRAT.
Table 4.
Comparisons between machine learning models with only BCRAT inputs.
Fig 2.
ROC curves for machine learning models with the broader set of inputs and for the BCRAT.
These are the receiver operating characteristic (ROC) curves for the six machine learning models with the broader set of inputs and for the Breast Cancer Risk Prediction Tool (BCRAT). The six machine learning models include a logistic regression (LR), naive Bayes (NB), decision tree (DT), linear discriminant analysis (LDA), support vector machine (SVM), and neural network (NN). We report Delong 95% confidence intervals for each area under the receiver operating characteristic curve (AUC) value.
Table 5.
Statistics for machine learning models with the broader set of inputs and for the BCRAT.
Table 6.
Comparisons between machine learning models with the broader set of inputs and the BCRAT.
Table 7.
Comparisons between machine learning models with the broader set of inputs.