Table 3.

The performance of the models developed by machine learning to evaluate the risk of pneumonia

Models	Sensitivity (%)	Specificity (%)	PPV (%)	NPV (%)	AUC
SVM	81.7	92.0	83.6	91.3	0.940
LR	58.7	99.0	97.5	84.3	0.931
MLP	71.8	92.0	82.7	87.9	0.923
RF	73.6	95.0	88.0	89.2	0.895

PPV positive predictive value, NPV negative predictive value, AUC area under curve, SVM support vector machine, LR logistic regression, MLP multi-layer perceptron, RF random forest