Table 2. The AUC of TIMI risk score and ML models with and without feature selection based on a 30% validation dataset.

Classifiers	The area under the ROC Curve (95% CI)
	In-hospital	30 days	1-year
RF	0.86 (0.820–0.88)	0.83 (0.786–0.879)	0.78 (0.741–0.827)
RFvarImp-SBE-RF	0.87 (0.832–0.907)	0.85 (0.10–0.890)	0.80 (0.750–0.834)
RFE-RF	0.86 (0.821–0.893)	0.82 (0.772–0.872)	0.79 (0.748–0.833)
SVM	0.86 (0.824–0.895)	0.87 (0.831–0.912)	0.84 (0.801–0.877)
SVMvarImp-SBE-SVM	0.88 (0.846–0.910)	0.90 (0.870–0.935)	0.84 (0.798–0.872)
RFE-SVM	0.85 (0.811–0.887)	0.88 (0.837–0.920)	0.84 (0.806–0.880)
LR	0.88 (0.846–0.911)	0.85 (0.803–0.897)	0.76 (0.710–0.807)
LRstepwise—SBE-LR	0.89 (0.861–0.920)	0.85 (0.812–0.906)	0.80 (0.767–0.848)
RFE- LR	0.87 (0.842–0.897)	0.83 (0.783–0.882)	0.78 (0.737–0.826)
TIMI	0.81 (0.772–0.802)	0.80 (0.746–0.838)	0.76 (0.715–0.802)

Abbreviations:

RF = Random Forest.

RFvarImp-SBE-RF = RF variable importance with sequential backward elimination and RF classifier.

RFE-RF = Recursive feature elimination with RFclassifier.

SVM = Support Vector Machine.

SVMvarImp-SBE-SVM = SVM variable importance with sequential backward elimination and SVM classifier.

RFE-SVM = Recursive feature elimination with SVM classifier.

LR = Logistic Regression.

LRstepwise—SBE-LR = LR stepwise feature elimination and LR classifier.

RFE- LR = Recursive feature elimination with LR classifier.

TIMI = Thrombolysis in Myocardial Infarction.