Guttmannova and Co-authors Publish a Machine Learning Study to Identify Predictors of Alcohol and Cannabis Impaired Driving
Posted: 3/19/2026 (CSDE Research)
In a new article in Alcohol: Clinical and Experimental Research, CSDE Affiliate Katarina Guttmannova (Psychiatry and Behavioral Sciences) and co-authors used machine learning to predict impaired driving among young adults in Washington. Data came from annual cross-sectional surveys of 18- to 25-year-olds participating in the Washington Young Adult Health Survey (2015–2022). For likelihood of alcohol-impaired driving, top predictors included alcohol use frequency, participants’ age, peak drinking quantity, age of alcohol initiation, full-time employment, and cannabis use frequency. For likelihood of cannabis-impaired driving, top predictors included cannabis use frequency, cannabis-related memory problems, simultaneous alcohol and cannabis use frequency, increased cannabis tolerance, and age of cannabis initiation. Two complementary machine learning methods yielded convergent findings on the most salient predictors of impaired driving, increasing confidence in their validity. These methods provide a flexible alternative to traditional models for analyzing high-dimensional data.