Chunk #40 — HOW DO NEURAL SIGNATURES ASSOCIATED WITH AUD HELP ELUCIDATE THE ROLE OF BRAIN FUNCTION IN THE RISK AND CONSEQUENCES OF ALCOHOL USE AND AUD ACROSS THE LIFESPAN? — How do these multi‐modal risk and protective factors fit together to influence the development and course of AUD?
Taking advantage of the wealth of our multimodal data and our interdisciplinary expertise, COGA has used machine learning (ML) methods as one approach to understand the interplay of complex factors involved in risk and resilience to as well as recovery from AUD. ML methods take an atheoretical approach to aggregating high‐dimensional data. 135 COGA has used ML algorithms to build models with the goal of identifying individuals at higher risk of developing AUD. For example, we reported that ML models combining EEG and AUD associated genetic variants outperformed other models based on a single type of data, suggesting that each contributed unique and significant information. 136 Using a Random Forests method, we found that EEG hyperconnectivity across the default mode network regions, PGS for AUD, alcohol consumption and related health consequences, elevated neuroticism, increased harm avoidance, and fewer positive life events could all be used to classify individuals who would develop alcohol induced memory problems 20 years later. 31 More recently, COGA has used ML algorithms to predict the difference in AUD recovery status, identifying several discriminative features, including PGS
