Table A2.

Accuracy values for classification of severe and non-severe COVID-19 based on chest radiographs in the held-out independent test sets by the Inception-v4 models trained with different training sets and batch sizes of 16 and 32. The mean and standard deviation were estimated from the models trained with five random initializations for a given training set and batch size.

Batch Size	Models	MIDRC	BrixIA	COVIDGR	UMICH
		Accuracy
16	M	0.77 ± 0.05	0.75 ± 0.08	0.82 ± 0.05	0.77 ± 0.06
	MB	0.80 ± 0.01	0.81 ± 0.02	0.74 ± 0.05	0.84 ± 0.01
	MBC	0.80 ± 0.02	0.79 ± 0.02	0.81 ± 0.05	0.83 ± 0.02
32	M	0.77 ± 0.03	0.78 ± 0.02	0.71 ± 0.07	0.80 ± 0.02
	MB	0.81 ± 0.02	0.79 ± 0.02	0.71 ± 0.02	0.83 ± 0.01
	MBC	0.80 ± 0.01	0.79 ± 0.01	0.80 ± 0.07	0.83 ± 0.03