Predicting treatment-seeking status for alcohol use disorder using polygenic scores and machine learning in a deeply-phenotyped sample.

Abstract

Few individuals with alcohol use disorder (AUD) receive treatment. Previous studies have shown drinking behavior, psychological problems, and substance dependence to predict treatment seeking. However, to date, no studies have incorporated polygenic scores (PGS), a measure of genetic risk for AUD. In a deeply-phenotyped sample, we identified 9103 individuals diagnosed with DSM-IV AUD and indicated treatment-seeking status. We implemented a random forest (RF) model to predict treatment-seeking based on 91 clinically relevant phenotypes. We calculated AUD PGS for those with genetic data (African ancestry [AFR] n = 3192, European ancestry [EUR] n = 3553) and generated RF models for each ancestry group, first without and then with PGS. Lastly, we developed models stratified by age (< and ≥40 years old). 66.6 % reported treatment seeking (M_age=40.0, 62.4 % male). Across models, top predictors included years of alcohol use and related psychological problems, psychiatric diagnoses, and heart disease. In the models without PGS, we found 77.6 % accuracy and 0.829 AUC for EUR and 75.1 % and 0.770 for AFR; the addition of PGS did not substantially change these metrics. PGS was the 9th most important predictor for EUR and 28th for AFR. In the age-stratified analysis, PGS ranked 8th for < 40 and 34th for ≥ 40 in EUR ancestry, and it ranked 70th for < 40 and 78th for ≥ 40 in the AFR sample. Alcohol use, psychiatric issues, and comorbid medical disorders were predictors of treatment seeking. Incorporating PGS did not substantially alter performance, but was a more important predictor in younger individuals with AUD.