Skip to main content
. 2022 Aug 25;25(1):92–100. doi: 10.1093/europace/euac145

Figure 2.

Figure 2

Random forest model selection. (A) Variable ranking for the 27 original predictors; (B) the number of included variables strengthens the model AUC reaching a plateau at 19; (C) ROC curve and corresponding AUC of the final 19-variable random forest model. AAD, antiarrhythmic drug; AFL, atrial flutter; AUC, area under the receiver operator curve; AFL, atrial flutter; BMI, body mass index; CAD, coronary artery disease; COPD, chronic obstructive pulmonary disease; LA, left atrium; LVEDV, left ventricular end-diastolic volume; LVEF: left ventricular ejection fraction; PAD, peripheral artery disease; RF: random forest; ROC: receiver operator curve.