Skip to main content
. 2018 Jun 18;12(6):e0006587. doi: 10.1371/journal.pntd.0006587

Fig 1. Framework of random forest algorithm.

Fig 1

1000 random bootstrap samples were drawn from the data, and an unpruned decision tree is fitted to each bootstrap sample. At each node, a small subset of the covariates was chosen at random to optimize the split. The predicted risk rank is obtained by averaging the prediction of all trees.