TABLE 7. Comparing the Performance Metrics Achieved With the Pruned and Unpruned Model Ensembles From Table 4.

Method	Method	Acc.	AUC	Sens.	Prec.	F	MCC
Majority Voting	Unpruned	0.9742	0.9807 [0.9686 0.9928]	0.9742	0.9748	0.9742	0.9537
	Pruned	0.9821	0.9866 [0.9765 0.9967]	0.9821	0.9822	0.9821	0.9676
Averaging	Unpruned	0.9782	0.9969 [0.992 1.0]	0.9782	0.9786	0.9782	0.9607
	Pruned	0.9821	0.9969 [0.992 1.0]	0.9821	0.9823	0.9821	0.9677
Weighted Averaging	Unpruned	0.9762	0.9968 [0.9918 1.0]	0.9762	0.9767	0.9762	0.9572
	Pruned	0.9901	0.9972 [0.9925 1.0]	0.9901	0.9901	0.9901	0.9820
Stacking	Unpruned	0.9663	0.9865 [0.9764 0.9966]	0.9663	0.968	0.9662	0.9402
	Pruned	0.9712	0.9876 [0.9779 0.9973]	0.9712	0.9711	0.9712	0.9473

* Bold values stand for the model with a statistically significant better performance than the other models.