during each bootstrap process, which is called the out-of-bag (OOB) sample. The classification error calculated from this sample is called the OOB error score. The aggregate of OOB scores from all decision trees will provide the ensemble OOB error rate (i.e., classification error) as well as the accuracy rate for the RF model. Thus, the OOB score provides a validation for the RF model. In the model, the maximum number of trees (‘ntree’) was set at 500. The optimal number of features analyzed at each node (‘Mtry’) was estimated to be 21 (using the ‘tuneRF’ function) and was used in the classifier algorithm. The final list of variables that significantly contributed for the classification was tabulated, and a 3-dimensional connectivity map of top significant DMN connections within a brain anatomical template was created using custom Matlab scripts.
