Table 5.

Comparison^a between single frame and multi-frame input for the EfficientNetB2 models using the internal test set. Optimal performance is highlighted in bold^b.

	Single-frame test			Multi-frame test
	Precision	Recall	$F1$-score	Precision	Recall	$F1$-score
CA	0.904 ± 0.002	0.906 ± 0.002	0.904 ± 0.002	0.933 ± 0.002	0.934 ± 0.002	0.933 ± 0.002
CP	0.923 ± 0.002	0.921 ± 0.002	0.919 ± 0.002	0.912 ± 0.002	0.912 ± 0.002	0.912 ± 0.002
Normal	0.863 ± 0.003	0.851 ± 0.003	0.851 ± 0.003	0.879 ± 0.003	0.874 ± 0.003	0.875 ± 0.003

^aPerformance metrics reported are bootstrap confidence intervals with 1000 iterations and a minimum sample size of 25% of the data.

^bBolded results are significantly different than their counterparts with at least one standard deviation of difference.