Table 5.

Performance of models applied with deviations

Study	Validation performance—reported from study	Validation performance—NYU data	Performance difference between study validation performance and NYU original validation performance	Validation performance—NYU retrained (95% CI)	Performance difference between study validation performance and NYU retrained validation performance	NYU deviations from original
Gong et al5	Cohort 1: AUROC=0.85	AUROC=0.59	AUROC difference=0.26	AUROC=0.68 (0.64 to 0.74)	AUROC difference=0.17	PaO2 data not available. Target excluded
Gong et al5	Cohort 2: AUROC=0.75	AUROC=0.60	AUROC difference=0.16	AUROC=0.68 (0.64 to 0.74)	AUROC difference=0.07	PaO2 data not available. Target excluded
Zhou et al8	AUROC=0.88	AUROC=0.74	AUROC difference=0.14	AUROC=0.75 (0.71 to 0.78)	AUROC difference=0.14	‘Severe respiratory distress’ target not characterisable. Target excluded
Zou et al9	*	AUROC=0.70	*	AUROC=0.72 (0.67 to 0.77)	*	Altered mental status measured as Glasgow Coma Score <15
	Mean AUROC=0.83	Mean AUROC=0.66	Mean AUROC difference=0.19	Mean AUROC=0.71	Mean AUROC difference=0.13

*Value unavailable because authors did not provide an AUROC value when reporting validation performance.

AUROC, area under the receiver–operator curve; NYU, New York University; PaO2, partial pressure of oxygen.