Fig. 3From: Validating biomarkers and models for epigenetic inference of alcohol consumption from bloodEpigenetic inference of alcohol consumption from blood based on newly developed models including all categories. Prediction accuracy for alcohol consumption expressed as Area Under the Curve (AUC) for A heavy and at-risk drinkers vs. light and non-drinkers and B heavy, at-risk and light drinkers vs. non-drinkers. In these models, all available participants from all categories were included, in contrast to Fig. 2. ‘Internal Validation’: Mean AUC and SD from internal validation using ten-fold cross-validation in our model building data set. ‘External Validation’: AUCs from external validation by applying our model trained in the model building dataset to independent data from three external validation cohorts (Rotterdam Study, N = 648; SHIP-Trend, N = 433; and TwinsUK, N = 713 and N = 442). For phenotype definition, see legend of Fig. 2. Abbreviations: RS- The Rotterdam Study; SHIP- Study of Health in Pomerania-Trend cohort; TwinsUK- The TwinsUK Study; TwinsUK2- Subset of the TwinsUK StudyBack to article page