Figure 10.

Decision tree graphical visualization. Graphical representation of our decision tree with maximum depth of five and used impurity criterion of entropy. In the decision-making process of the decision tree, we can observe the importance of the parameter RQAdet_ap to discriminate between Parkinson’s and healthy subjects in root node. As can be observed from the internal nodes, HR_ap, and RQAdet_ap are very important in the forecasting process: HR_ap, harmonic ratio anteroposterior; RQAdet_ap, % determinism in the recurrence quantification analysis anteroposterior; pwPD, people with Parkinson’s disease; HS, healthy subjects.