Table 2. Comparison of different classification methods.

	Sensitivity (95% CI)	Specificity (95% CI)	AUC (95% CI)
Brighton Collaboration
ABC tool*	0.64 (0.52–0.75)	0.97 (0.96–0.98)	NA
Ontology Classification	0.57 (0.51–0.64)	0.97 (0.96–0.97)	0.77 (0.74–0.80)
IR approach*	0.86 (0.75–0.93)	0.7861 (0.76–0.80)	NA
SMQ
SMQ categories (combined)*	0.54 (0.42–0.66)	0.97 (0.96–0.98)	NA
IR approach*	0.85 (0.73–0.92)	0.86 (0.84–0.87)	NA
Expanded SMQ	0.92 (0.89–0.95)	0.88 (0.87–0.89)	0.96 (0.95–0.97)

*indicates that the result was taken from [19] (values for the testing set). In the Brighton Collaboration section, the ABC tool and ontology-based classification have similar outputs (the small difference in terms of sensitivity can be explained as Botsis et al. split their dataset into training and testing). In the SMQ section, the expanded SMQ yields better results in terms of sensitivity and specificity compared to the existing SMQ categories and the IR approach proposed in [19]. CI: confidence interval.