Random Forest and Concept of Decision Tree Model

Abstract

The method of random forest (RF) is a generalized advanced decision trees methods or techniques in which the clinical data space recursively portioned (usually binary split) according to the values of one or more predictor variables, such that the observations within a portion becomes more and more homogeneous. Moreover, the RF techniques come with a built-in protection against the overfitting by using a part of the data sets that each tree in the forest has not been calculated by its goodness of fit. Thus, the RF is a more reliable method extract decision-making approach for clinical research (in vivo or in vitro). In this regard, this chapter describes various aspects of random forest on real applications towards clinical and life science research; the model has been demonstrated by real data sets, and we also explored practical application of random forest for solving the real problems of clinical research. We examined how basic decision trees work, how individual decisions trees are combined to make a random forest, and ultimately discover why random forests are so good at what they do. Many illustrations and eye-catching figures accord to describe the model building. Summing of the research findings, the Random forests is advanced tool for clinical research each individual tree to create an uncorrelated forest of trees whose prediction by committee is more accurate than that of any individual tree.