Robust Predictive Models in Clinical Data—Random Forest and Support Vector Machines

In this chapter, we aim to explain the principles that make random forest (RF) and support vector machines (SVMs) successful modelling and prediction tools for a variety of applications. We try to achieve this by presenting the basic ideas of RF and SVMs, together with an illustrative example using the MIMIC III database. The advantages and limitations of both methods are discussed in the chapter. The chapter provides some guidance for choosing a machine learning model, building and training the model, validating model performance and interpreting the results with the Python programming language.