 This research proposes a new graph kernel called the Ordinal Pattern kernel, OPK, to measure the similarity of two brain connectivity networks. OPK takes into account both the topological structure and the edge weights of the networks, allowing for more accurate diagnoses of mild cognitive impairment, MCI. This kernel was tested against other graph kernels and found to be superior in terms of accuracy in classifying MCI patients. This article was authored by Kaima, Shuo Huang, and Dacheng Zhang.