Table 1 Predictive performance comparisons with different learning methods in Dataset 1.

Prediction performance in dataset 1	Method	Sigmoid-SVM			Poly-SVM			RBF-SVM
	Method	Side Effects(SE)	Indications	SE + Indications	Side Effects(SE)	Indications	SE + Indications	Side Effects(SE)	Indications	SE + Indications
		Prediction	Prediction	Prediction	Prediction	Prediction	Prediction	Prediction	Prediction	Prediction
	AUC	0.42 ± 0.08	0.79 ± 0.12	0.5252 ± 0.13	0.792 ± 0.12	0.81 ± 0.18	0.84 ± 0.09	0.88 ± 0.57	0.798 ± 0.21	0.84 ± 0.11
	Accuracy	0.495 ± 0.15	0.51 ± 0.11	0.52 ± 0.17	0.72 ± 0.1	0.63 ± 0.14	0.73 ± 0.08	0.89 ± 0.46	0.77 ± 0.11	0.74 ± 0.11
	F1	0.481 ± 0.17	0.5514 ± 0.12	0.607 ± 0.08	0.584 ± 0.14	0.37 ± 0.21	0.58 ± 0.11	0.76 ± 0.31	0.641 ± 0.15	0.73 ± 0.11
	Method	KNN			Decision Tree (DT)			Deep Learning
	Method	Side Effects(SE)	Indications	SE + Indications	Side Effects(SE)	Indications	SE + Indications	Side Effects(SE)	Indications	SE + Indications
		Prediction	Prediction	Prediction	Prediction	Prediction	Prediction	Prediction	Prediction	Prediction
	AUC	0.795 ± 0.11	0.82 ± 0.08	0.791 ± 0.13	0.64 ± 0.15	0.69 ± 0.16	0.633 ± 0.09	0.98 ± 0.02	0.98 ± 0.01	0.979 ± 0.02
	Accuracy	0.806 ± 0.08	0.71 ± 0.13	0.74 ± 0.11	0.574 ± 0.12	0.69 ± 0.14	0.58 ± 0.12	0.96 ± 0.02	0.965 ± 0.03	0.96 ± 0.02
	F1	0.712 ± 0.07	0.68 ± 0.09	0.717 ± 0.09	0.567 ± 0.12	0.661 ± 0.09	0.568 ± 0.12	0.902 ± 0.06	0.891 ± 0.09	0.904 ± 0.04

Each test data field shows average ± std of 1000 random splits of training and test data.

Quick links

Search