Fig. 2: ROC curves for baseline and PRS models. | Translational Psychiatry

Fig. 2: ROC curves for baseline and PRS models.

From: Using polygenic scores for identifying individuals at increased risk of substance use disorders in clinical and population samples

Fig. 2

Receiver operating characteristic (ROC) curves for baseline models (covariates only) and polygenic risk score (PRS) models (PRS + covariate) for each level of severity in alcohol use disorder (AUD). Area under the curve (AUC) for the PRS model (Full AUC) and change in in AUC from Base to PRS model (Δ AUC) is presented each cell. AUC provides an estimate of the probability a randomly selected subject with the condition has a test result indicating greater suspicion than that of a randomly chosen subject without the condition29. An AUC of 0.5 indicates that a classifier does not provide any useful information in determining cases from controls.

Back to article page