A Study of Machine-Learning Classifiers for Hypertension Based on Radial Pulse Wave

Figure 6

The importance of the classification variables features. The bar charts (a), (b), and (c) represent the results of feature importance of AdaBoost, Gradient Boosting, and Random Forest (RF), respectively. The y-axis represents the value of the importance for variables features. Note that “yes" represents that K-means is used to reduce noise in this model and vice versa.

(a)

(b)

(c)