Figure 3
Comparison of models for predicting incident atrial fibrillation based on the c-index. DNN deep neural network model, DT decision tree model, NB naïve Bayes model, PM2.5 particulate matter < 2.5 μm in diameter, RF random forest model, SVM support vector machine, TR1 traditional regression analysis model using clinical six variables (adjusted variables were same with that of TR1 (model 1) in Table 2) as input variables, TR2 traditional regression analysis model using clinical 12 variables (adjusted variables were same with that of TR2 (model 2) in Table 2), XGBM extreme gradient boosting model.
