Random forest Granger causality for detection of effective brain connectivity using high-dimensional data.

Studies have shown that the brain functions are not localized to isolated areas and connections but rather depend on the intricate network of connections and regions inside the brain. These networks are commonly analyzed using Granger causality (GC) that utilizes the ordinary least squares (OLS) method for its standard implementation. In the past, several approaches have shown to solve the limitations of OLS by using diverse regularization systems. However, there are still some shortcomings in terms of accuracy, precision, and false discovery rate (FDR). In this paper, we are proposing a new strategy to use Random Forest as a regularization technique for computing GC that will improve these shortcomings. We have demonstrated the effectiveness of our proposed methodology by comparing the results with existing Least absolute shrinkage and selection operator (LASSO), and Elastic-Net regularized implementations of GC using simulated dataset. Later, we have used our proposed approach to map the network involved during deductive reasoning using real StarPlus dataset.