Table 4 Case study of the AD patient stratification, accuracy between gene expression and proposed method integrated four kernels (different kernel functions: k1 = Gaussians, k2 = Polynomial, k3 = Linear, k4 = Sigmoid). fMKL-DR is the best accuracy among the 20 runs, and fMKL-DR^a is accuracy tested at 95% confidence level

From: Stratifying patients using fast multiple kernel learning framework: case studies of Alzheimer’s disease and cancers