Table 6.

AUC 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
		AUC
16	M	0.82 ± 0.09	0.79 ± 0.14	0.82 ± 0.15	0.82 ± 0.10
	MB	0.86 ± 0.01	0.88 ± 0.01	0.79 ± 0.04	0.89 ± 0.01
	MBC	0.88 ± 0.01	0.87 ± 0.01	0.84 ± 0.02	0.89 ± 0.01
32	M	0.84 ± 0.03	0.85 ± 0.01	0.74 ± 0.05	0.87 ± 0.02
	MB	0.88 ± 0.02	0.88 ± 0.01	0.79 ± 0.03	0.89 ± 0.02
	MBC	0.87 ± 0.01	0.88 ± 0.01	0.85 ± 0.06	0.89 ± 0.01