Table 6.

Deep learning clinical outcome prediction results.

		Ventilation Requirement		Mortality
		Unadjusted	Histogram Matching	Unadjusted	Histogram Matching
Sensitivity	CXR	0.55 ± 0.09	0.64 ± 0.09	0.56 ± 0.15	0.59 ± 0.13
	CLC	0.63 ± 0.08	0.61 ± 0.01	0.58 ± 0.17	0.67 ± 0.09
	REM	0.54 ± 0.08	0.68 ± 0.05	0.66 ± 0.07	0.64 ± 0.07
	REM CLC	0.58 ± 0.09	0.62 ± 0.08	0.61 ± 0.14	0.77 ± 0.07
	RAD	0.63 ± 0.06	0.66 ± 0.04	0.58 ± 0.12	0.59 ± 0.12
	RAD CLC	0.62 ± 0.07	0.67 ± 0.07	0.59 ± 0.07	0.69 ± 0.08
Specificity	CXR	0.72 ± 0.08	0.73 ± 0.07	0.72 ± 0.07	0.74 ± 0.04
	CLC	0.66 ± 0.08	0.76 ± 0.05	0.65 ± 0.06	0.71 ± 0.09
	REM	0.59 ± 0.05	0.63 ± 0.02	0.58 ± 0.08	0.73 ± 0.07
	REM CLC	0.65 ± 0.07	0.68 ± 0.06	0.63 ± 0.08	0.60 ± 0.09
	RAD	0.69 ± 0.06	0.75 ± 0.06	0.67 ± 0.03	0.76 ± 0.03
	RAD CLC	0.69 ± 0.06	0.78 ± 0.05	0.71 ± 0.02	0.67 ± 0.03
AUC	CXR	0.70 ± 0.07	0.75 ± 0.02	0.72 ± 0.07	0.75 ± 0.04
	CLC	0.69 ± 0.03	0.77 ± 0.02	0.70 ± 0.07	0.74 ± 0.04
	REM	0.61 ± 0.03	0.71 ± 0.02	0.67 ± 0.04	0.76 ± 0.04
	REM CLC	0.64 ± 0.02	0.72 ± 0.02	0.68 ± 0.02	0.77 ± 0.01
	RAD	0.70 ± 0.03	0.77 ± 0.03	0.69 ± 0.07	0.74 ± 0.06
	RAD CLC	0.72 ± 0.02	0.78 ± 0.02	0.71 ± 0.04	0.75 ± 0.07

All columns used preprocessed patient CXRs as inputs to DL networks in addition to: CLC―clinical features including patient age and sex; REM―radiomic-embedded feature maps; RAD―concatenation of radiomic features to DL feature outputs. Bold text indicates highest metrics obtained.