Related Experiment Video
Updated: May 2, 2026
07:51
A Protocol for Measuring Cue Reactivity in a Rat Model of Cocaine Use Disorder
Published on: June 18, 2018
10.2K
A Machine Learning Based Causal Interface for Time Varying Environmental Predictors of Substance Use Initiation in
Mengman Wei1, Lasya Yadlapati1,2, Qian Peng1
1Department of Neuroscience, The Scripps Research Institute, 10550 N Torrey Pines Rd, La Jolla, 92037, CA, U.S.
Summary
This study identifies key predictors of adolescent substance use initiation using advanced machine learning and causal inference. Findings highlight modifiable factors like sleep and family environment for prevention strategies.
Area of Science:
- Adolescent development
- Substance use research
- Causal inference
Background:
- Adolescent Brain Cognitive Development (ABCD) Study provides longitudinal data on substance use initiation.
- Classical models struggle with high-dimensional, correlated predictors.
Purpose of the Study:
- Develop a practical framework for analyzing high-dimensional longitudinal data on substance use initiation.
- Identify time-varying environmental, genetic, and behavioral predictors of substance use.
Main Methods:
- Utilized a two-stage machine learning framework on 11,868 ABCD participants.
- Employed Granger-inspired graph discovery and Double Machine Learning (DML) with cross-fitting for effect estimation.
- Analyzed lagged variables to ensure temporal order and used random forests for nuisance function estimation.
Main Results:
- Identified stable predictors across sleep, family, peers, behavior, and genetics.
- Observed modest effect sizes ( -0.01 to 0.02) for predictors, with both risk-increasing and protective associations.
- Sleep disturbance and behavioral risks were risk factors; parental monitoring and structured environments were protective.
Conclusions:
- Presents a viable machine learning approach for high-dimensional longitudinal causal inference.
- Highlights shared and substance-specific risk factors for adolescent substance use.
- Identifies modifiable targets, including sleep and family environment, for prevention.
Related Concept Videos
01:17Drug Dependence
1.9K
Medications are typically administered to achieve therapeutic effects. Some drugs can modify an individual's mood and perception, frequently resulting in various enjoyable experiences. However, this can result in drug dependency, a condition marked by continuous drug use despite potential negative consequences. Drug dependency primarily falls into two categories: psychological and physical dependence. Psychological dependence occurs when the pleasurable feelings induced by the drug...
1.9K
01:21Causality in Epidemiology
2.2K
Causality or causation is a fundamental concept in epidemiology, vital for understanding the relationships between various factors and health outcomes. Despite its importance, there's no single, universally accepted definition of causality within the discipline. Drawing from a systematic review, causality in epidemiology encompasses several definitions, including production, necessary and sufficient, sufficient-component, counterfactual, and probabilistic models. Each has its strengths and...
2.2K
01:15Drug Concentration Versus Time Correlation
3.0K
The plasma drug concentration-time curve is a crucial tool in pharmacokinetics, representing the drug's concentration in plasma at different time intervals post-administration. This curve illustrates the drug's journey from absorption into the systemic circulation, distribution to body tissues, and eventual elimination through excretion or biotransformation.
Two pivotal parameters are the minimum effective concentration (MEC) and the minimum toxic concentration (MTC). The MEC is the...
Two pivotal parameters are the minimum effective concentration (MEC) and the minimum toxic concentration (MTC). The MEC is the...
3.0K