Figure 1 | npj Genomic Medicine

Figure 1

From: Machine-learning approach identifies a pattern of gene expression in peripheral blood that can accurately detect ischaemic stroke

Figure 1

Top 50 genes selected by GA/kNN for identification of AIS. (a) The top 50 peripheral blood transcripts ranked by GA/kNN based on their ability to discriminate between AIS patients and neurologically asymptomatic controls in the discovery cohort. (b) Combined ability of the expression levels of top 50 genes selected by GA/kNN to discriminate between AIS patients and neurologically asymptomatic controls in the discovery cohort using kNN. (c) Ability of the expression levels of the top 50 genes selected by GA/kNN to discriminate between neurologically asymptomatic controls and AIS patients via kNN compared with the expression levels of genes selected at random. The accuracy of the top 10 genes selected by GA/kNN was specifically tested against the accuracy of randomly selected genes using single sample two-way t-test.

Back to article page