Table 4. Predictive performance of different machine learning algorithms for the training and test datasets.

Algorithm	Dataset	Number	Accuracy (%)	Sensitivity (%)	Specificity (%)	AUC
Logistic regression	Training	8644	62.20	62.05	62.36	0.6783
	Test	8644	62.78	61.81	63.12	0.6766
Random forest	Training	8644	83.39	83.02	83.76	0.9197
	Test	8644	64.78	66.58	64.16	0.7208

AUC, area under the receiver operating characteristics curve.