Table 2.

Performance of machine learning model to identify individuals who received autoantibody testing in the validation and external test datasets

Dataset	Total n	Autoantibody tested, n (%)	AUROC (95% CI)	Sensitivity (95% CI)	Specificity (95% CI)	Accuracy (95% CI)	NPV (95% CI)	PPV (95% CI)	F1 score
Validation (BioMe cohort 1)	25,062	5792 (23)	0.93 (0.93 − 0.93)	0.90 (0.90 − 0.90)	0.87 (0.87 − 0.88)	0.89 (0.88 − 0.89)	0.90 (0.89 − 0.90)	0.88 (0.87 − 0.88)	0.89 (0.88 − 0.89)
External test (All of Us)	136,522	19,264 (14)	0.87 (0.87 − 0.88)	0.82 (0.82 − 0.83)	0.82 (0.81 − 0.82)	0.82 (0.82 − 0.82)	0.82 (0.82 − 0.82)	0.82 (0.82 − 0.82)	0.83 (0.82 − 0.82)

n number, AUROC area under the receiver operating characteristic curve, NPV negative predictive value, PPV positive predictive value.