Table 2. Analysis of model performance over 6-hour and 12-hour prediction horizon.

COVID-19 Positives (6 hours)
Dataset	CRW	Emory	MLH
AUC	0.90 [0.889, 0.90]	0.85 [0.85, 0.86]	0.88 [0.86, 0.90]
Specificity	0.86 [0.86, 0.86]	0.81 [0.80,0.82]	0.82 [0.80, 0.84]
Sensitivity	0.77 [0.76,0.78]	0.74 [0.73, 0.76]	0.77 [0.74, 0.78]
PPV	0.54 [0.53, 0.54]	0.55 [0.54, 0.59]	0.56 [0.53, 0.59]
COVID-19 Positives (12 Hours)
Dataset	CRW	Emory	MLH
AUC	0.89 [0.88, 0.90]	0.82 [0.81, 0.83]	0.89 [0.87, 0.90]
Specificity	0.85 [0.85 0.86]	0.80 [0.79, 0.82]	0.81 [0.79, 0.84]
Sensitivity	0.77 [0.75, 0.78]	0.70 [0.69, 0.71]	0.77 [0.74, 0.80]
PPV	0.53 [0.52, 0.54]	0.54 [0.52, 0.55]	0.55 [0.52, 0.59]
All-cause ARDS (12 Hours)
Dataset	CRW	Emory	MLH
AUC	0.86 [0.85, 0.86]	0.80 [0.79, 0.81]	0.86 [0.84, 0.87]
Specificity	0.79 [0.79, 0.80]	0.77 [0.76, 0.78]	0.79 [0.76, 0.81]
Sensitivity	0.77 [0.76, 0.77]	0.70 [0.69, 0.71]	0.75 [0.72, 0.78]
PPV	0.45 [0.44, 0.45]	0.49 [0.48, 0.51]	0.51 [0.48, 0.55]