Table 3

Discrimination of breast cancer patients from normal controls using machine learning techniques. The mean and SD of five 20-fold cross-validation trials.

AlgorithmMaximal accuracy (%)SensitivitySpecificityNumber of SNPsa used for maximal accuracy
Naïve Bayes67 ± 254 ± 2%79 ± 2%3
Decision tree68 ± 164 ± 2%70 ± 4%2
SVM linear kernel62 ± 257 ± 2%57 ± 2%60
SVM quadratic kernel69 ± 453 ± 2%83 ± 7%3
SVM cubic kernel67 ± 447 ± 2%84 ± 4%3
  • a SNP, single nucleotide polymorphism; SVM, support vector machine.