The diagnosis of neurological diseases such as Parkinson's disease (PD) is commonly based on medical observations and assessment of clinical signs, including the characterization of a variety of motor symptoms. However, this type of diagnosis often depends on the person being evaluated, making the analyzes subjective. To deal with these problems and refine the procedures for the diagnosis and evaluation of neurological diseases, machine learning methods have been implemented for classifying and differentiating the levels of the disease. The R mlr3 package and its extension packages implement a powerful, object-oriented and extensible framework for machine learning (ML) in R. It provides a unified interface to many available learning algorithms, augmenting them with general-purpose, model-independent functionality, e.g., training test evaluation, resampling, preprocessing, hyperparameter tuning, nested resampling, and results visualization. In this article, an example of the use of this package will be presented, which may later help in the classification of motor signs in Parkinson's Disease.