Innovative Identification of Substance Use Predictors: Machine Learning in a National Sample of Mexican Children.

Machine learning provides a method of identifying factors that discriminate between substance users and non-users potentially improving our ability to match need with available prevention services within context with limited resources. Our aim was to utilize machine learning to identify high impact factors that best discriminate between substance users and non-users among a national sample (N = 52,171) of Mexican children (i.e., 5th, 6th grade; Mage = 10.40, SDage = 0.82). Participants reported information on individual factors (e.g., gender, grade, religiosity, sensation seeking, self-esteem, perceived risk of substance use), socioecological factors (e.g., neighborhood quality, community type, peer influences, parenting), and lifetime substance use (i.e., alcohol, tobacco, marijuana, inhalant). Findings suggest that best friend and father illicit substance use (i.e., drugs other than tobacco or alcohol) and respondent sex (i.e., boys) were consistent and important discriminators between children who tried substances and those that did not. Friend cigarette use was a strong predictor of lifetime use of alcohol, tobacco, and marijuana. Friend alcohol use was specifically predictive of lifetime alcohol and tobacco use. Perceived danger of engaging in frequent alcohol and inhalant use predicted lifetime alcohol and inhalant use. Overall, findings suggest that best friend and father illicit substance use and respondent's sex appear to be high impact screening questions associated with substance initiation during childhood for Mexican youths. These data help practitioners narrow prevention efforts by helping identify youth at highest risk.

The influence of perceived parenting on substance initiation among Mexican children.

Parents shape their children's behaviors and impact their developmental trajectories. Despite this, few studies have examined the potential relationship between child reported parenting factors and lifetime substance use and use intentions. The current study examined the potential impact of parenting factors (i.e., positive parenting, supervision, parental illicit substance use, substance-specific communication) on early substance use and intentions among Latinx children. Data for the present study utilized a representative sample of Mexican children (n = 52,171; 5th and 6th grades) who participated in a national survey on substance use. Children reported their demographics, lifetime substance use/intentions, and perceived parenting characteristic and practices. Child reported parental (i.e., individual or both parents) illicit substance use was associated with the largest increases in risk for reporting lifetime use of all substances examined. Higher levels of positive parenting were consistently associated with reductions in risk for reporting intentions for and use of all substances examined. Parent-child substance specific communication was not significantly related to child reported lifetime use or use intentions, with the exception of a minor decrease in the odds of reporting lifetime inhalant use. Supervision was associated with small to modest increase in risk. Substance use prevention efforts targeting Latinx populations may benefit from promoting positive parenting and direct supervision during childhood. Targeted prevention efforts may be needed for Latinx children exposed to parental illicit substance use, as they may be especially at risk for early substance initiation.