Fig. 4
ROC curves for predicting amyloid status. PRSnoAPOE+APOEε2+ε4 (with pT = 5 × 10−8) with age and sex was numerically the best performing model at predicting individuals who were amyloid negative at both time points, on the one hand, from individuals who were amyloid negative at baseline and positive at follow-up or amyloid positive at both time points, on the other hand. Abbreviations: AUC, area under the curve; CI, confidence interval; ROC, receiver operating characteristic