Table 5.

Evaluation results of different processing methods under different scenarios of MAR (the ratio of missing proportion 1:2) mechanism

Evaluation metrics	Missing proportions	Machine learning methods					Traditional methods
		LR	RF	NN	SVM	EL	Mode	KNN	MICE
sensitivity	0.05	0.870	0.874	0.874	0.870	0.874	0.866	0.870	0.871
	0.10	0.877	0.877	0.877	0.877	0.877	0.866	0.877	0.873
	0.15	0.885	0.881	0.889	0.881	0.889	0.866	0.877	0.882
	0.20	0.874	0.874	0.874	0.874	0.877	0.870	0.870	0.875
	0.30	0.897	0.885	0.877	0.874	0.900	0.805	0.870	0.878
	0.50	0.885	0.866	0.866	0.866	0.893	0.766	0.866	0.852
	Average	0.881	0.876	0.876	0.874	0.885	0.840	0.872	0.872
AUC	0.05	0.912	0.914	0.914	0.912	0.915	0.911	0.912	0.913
	0.10	0.917	0.916	0.916	0.916	0.917	0.917	0.917	0.914
	0.15	0.910	0.916	0.917	0.915	0.917	0.915	0.914	0.915
	0.20	0.912	0.914	0.914	0.914	0.916	0.909	0.911	0.913
	0.30	0.921	0.919	0.913	0.913	0.922	0.911	0.908	0.914
	0.50	0.924	0.914	0.913	0.915	0.925	0.912	0.916	0.909
	Average	0.916	0.916	0.915	0.914	0.919	0.913	0.913	0.913
Kappa	0.05	0.556	0.558	0.558	0.556	0.558	0.564	0.556	0.556
	0.10	0.564	0.564	0.564	0.564	0.564	0.580	0.566	0.562
	0.15	0.560	0.557	0.562	0.557	0.562	0.580	0.564	0.557
	0.20	0.554	0.554	0.555	0.554	0.556	0.539	0.552	0.548
	0.30	0.572	0.565	0.571	0.559	0.574	0.629	0.564	0.560
	0.50	0.560	0.548	0.549	0.548	0.564	0.632	0.552	0.540
	Average	0.561	0.558	0.560	0.556	0.563	0.587	0.559	0.554