Environmental, Health, and Psychological Factors Predict Alcohol Sipping in Childhood: A Machine Learning Analysis of...

Extant research has focused on the risk factors for alcohol use in adolescence, but little work has examined these in childhood. Early alcohol sipping, defined here as sipping alcohol by ages 9 to 10, may be a unique and informative developmental precursor to future problematic alcohol use. This study employed machine learning to rank risk factors linked to early alcohol sipping by importance.

Data from a subset of the Adolescent Brain Cognitive Development℠ (ABCD) Study sample were used (n = 10,707 children ages 9-10 years old; 48.1% girls). Two state-of-the-art machine learning techniques, eXtreme Gradient Boosting (XGBoost) and Shapley Additive exPlanations (SHAP), were combined to rank 341 environmental, 359 health, and 127 psychological factors and 1,332 indicators of brain function by their importance in classifying children with early alcohol sipping.

The environmental classification model yielded the highest classification performance (area under the curve = 0.76; 95% CI, 0.749-0.774). Factors related to family norms, socioeconomic status, parental stress, and maternal alcohol use were most important for identifying a child with early alcohol sipping. The health classification model had the second highest performance (area under the curve = 0.68; 95% CI, 0.662-0.690), with sleep patterns, early puberty onset, and mental health symptoms the most important for classifying early sipping. The psychological model yielded the third highest classification performance (area under the curve = 0.65; 95% CI, 0.638-0.667) and linked negative affect, sensation seeking, impulsivity, and impaired reward processing to sipping. Models that included brain indices performed only marginally better than chance.

Taken together, these results suggest that the factors underlying early alcohol sipping are similar to the factors underlying problematic alcohol use later in life and that interventions targeting these early in life may be effective at preventing future alcohol use.

We worked to ensure sex and gender balance in the recruitment of human participants. We worked to ensure race, ethnic, and/or other types of diversity in the recruitment of human participants. We worked to ensure that the study questionnaires were prepared in an inclusive way. We worked to ensure sex balance in the selection of non-human subjects. One or more of the authors of this paper self-identifies as a member of one or more historically underrepresented racial and/or ethnic groups in science. One or more of the authors of this paper self-identifies as a member of one or more historically underrepresented sexual and/or gender groups in science. One or more of the authors of this paper self-identifies as living with a disability. We actively worked to promote sex and gender balance in our author group. One or more of the authors of this paper received support from a program designed to increase minority representation in science. We actively worked to promote inclusion of historically underrepresented racial and/or ethnic groups in science in our author group. While citing references scientifically relevant for this work, we also actively worked to promote sex and gender balance in our reference list. While citing references scientifically relevant for this work, we also actively worked to promote inclusion of historically underrepresented racial and/or ethnic groups in science in our reference list. The author list of this paper includes contributors from the location and/or community where the research was conducted who participated in the data collection, design, analysis, and/or interpretation of the work.