Table 2 Metrics for all classification models. 95% confidence intervals (95% CI) derived from 500 bootstraps by using all variables. Selected models are highlighted in bold

LR

0.90 (0.89–0.91)

0.23 (0.20–0.26)

0.81 (0.78–0.84)

0.82 (0.82–0.83)

0.82 (0.80–0.83)

0.55 (0.54–0.56)

Xgboost

0.90 (0.89–0.91)

0.23 (0.20–0.26)

0.82 (0.79–0.85)

0.81 (0.81–0.82)

0.82 (0.80–0.83)

0.55 (0.54–0.57)

SVM

0.90 (0.88–0.91)

0.22 (0.20–0.25)

0.81 (0.78–0.83)

0.82 (0.81–0.82)

0.81 (0.80–0.82)

0.55 (0.54–0.57)

NB

0.80 (0.79–0.81)

0.43 (0.42–0.46)

0.91 (0.88–0.93)

0.59 (0.59–0.60)

0.75 (0.74–0.76)

0.43 (0.42–0.43)

Light-GBM

0.87 (0.86–0.89)

0.20 (0.18–0.24)

0.55 (0.51–0.58)

0.91 (0.91–0.92)

0.73 (0.71–0.75)

0.60 (0.59–0.61)

RF

0.79 (0.77–0.80)

0.34 (0.32–0.36)

0.75 (0.72–0.78)

0.69 (0.69–0.7)

0.72 (0.71–0.74)

0.50 (0.50–0.50)

MLP

0.86 (0.85–0.87)

0.19 (0.17–0.22)

0.36 (0.33–0.39)

0.96 (0.96–0.97)

0.66 (0.66–0.68)

0.63 (0.61–0.64)

KNN

0.75 (0.73–0.77)

0.18 (0.16–0.20)

0.14 (0.11–0.16)

0.98 (0.98–0.99)

0.56 (0.55–0.57)

0.57 (0.56–0.58)

DC

0.51 (0.49–0.53)

0.28 (0.26–0.30)

0.52 (0.48–0.55)

0.50 (0.50–0.51)

0.51 (0.49–0.53)

0.36 (0.36–0.36)