predicting diagnosis, clinical outcomes, and classifying disorders such as depression 6, schizophrenia 4, 8, and AUD 9–11. Specifically, AUD classifiers achieved significant accuracy utilizing electrophysiological features such as EEG coherence and spectral power (89.3%)10, 11, EEG’s nonlinear features (91.7%) 9, family history (FH) of AUD and psycho-social features 3, 7, as well as genetic information 3, 12. However, there are no longitudinal studies that analyzed the predictive model of AUD based on data acquired prior to its development, thus, avoiding the confounding with effects of AUD. Such a model can give important information about biomarkers which can indicate the sensitivity to develop AUD. The current study used longitudinal multidimensional data from COGA (e.g., clinical, electrophysiological, SNP, FH), including individuals of European American (EA) and African American (AA) ancestry. COGA collects data and follows AUD/non-AUD individuals starting as early as age 12, enabling a unique opportunity to compare individual’s status before and after AUD developed.
