Figure 1From: Using a multi-staged strategy based on machine learning and mathematical modeling to predict genotype-phenotype risk patterns in diabetic kidney disease: a prospective case–control cohort analysis Ten-fold cross-validation predictive performance by different machine learning methods in the DKD training dataset using A) clinical and genetic attributes, B) genetic-only attributes, C) clinical-only attributes. Abbreviations – svmradial: support vector machine using radial basis kernel function, rpart: recursive partitioning and regression trees, nnet: feed-forward neural networks and multinomial log-linear models, nb: naïve Bayes classifier, cforest: random forest utilizing conditional inference trees as base learners, C5.0 Tree: C5.0 decision tree, pls: partial least squares regression.Back to article page