Skip to main content
Fig. 4 | BMC Medical Informatics and Decision Making

Fig. 4

From: The prediction of asymptomatic carotid atherosclerosis with electronic health records: a comparative study of six machine learning models

Fig. 4

19 features used for decision tree model generation and their information gain values. Features were ranked according to their information gain values which reflect the entropy gain with respect to the predictive outcome. The longer the blue transverse column (the higher the value), the greater importance on the outcome. (SBP, systolic blood pressure; HDL, high density lipoprotein; TC, total cholesterol; γ-GLT, γ-glutamyl transpeptidase)

Back to article page