Table 4:

MIMIC-III results (top-50 codes). The results of MultiResCNN are shown in means ± standard deviations.

Model	AUC		F1		P@5
	Macro	Micro	Macro	Micro
C-MemNN (Prakash et al. 2017)	0.833	-	-	-	0.420
C-LSTM-Att (Shi et al. 2017)	-	0.900	-	0.532	-
CAML (Mullenbach et al. 2018)	0.875	0.909	0.532	0.614	0.609
DR-CAML (Mullenbach et al. 2018)	0.884	0.916	0.576	0.633	0.618
MultiResCNN	0.899	0.928	0.606	0.670	0.641
	±0.004	±0.002	±0.011	±0.003	±0.001