Identification of Prospective Predictors of Alcohol Initiation During Early Adolescence
Identification of Prospective Predictors of Alcohol Initiation During Early Adolescence
批准号:
10823917
负责人:
Andrew Moore
金额:
$4.21万
依托单位:
依托单位国家:
美国
项目类别:
财政年份:
2024
资助国家:
美国
项目状态:
未结题
起止时间:
2024-01-01 至 2025-12-31
关键词:
10 year oldAddressAdolescentAgeAlcohol consumptionAlcoholsAmericanAttitudeBrainChildClassificationConsumptionDataData AnalysesData SetDevelopmentDiagnosisEarly InterventionEnvironmental ImpactEnvironmental Risk FactorEquationFactor AnalysisFutureGoalsIndividualInterventionInvestigationLifeLiteratureMachine LearningMeasuresMediatingMethodsModelingNational Institute on Alcohol Abuse and AlcoholismNeurocognitiveOutcomeParticipantPredictive FactorPreventionResearchResearch PersonnelRewardsRiskRisk FactorsSamplingTechniquesTestingTimeWeightWorkYouthalcohol availabilityalcohol riskalcohol use disorderalcohol use initiationcognitive developmentdata-driven modelearly adolescencemachine learning modelmultidimensional dataneuroimagingneurophysiologynovelpeerpreadolescencepreventprospectiverandom forestunderage drinking
中文摘要
项目摘要/摘要
国家酒精滥用和酒精中毒研究所最近的倡议侧重于预防
儿童和青少年饮酒问题。为了解决这一问题,拟议的项目侧重于确定突出的、
早期开始饮酒(EAI)或饮用全量饮料的前瞻性预测因素和推断原因
在16岁之前含酒精。拟议项目的目标将测试当前的假设
酒精开始的预测因素(目标1a),比较先验风险因素和新的数据驱动的风险因素(目标1b),
推断因素和EAI之间的因果关系(目标2),作为探索性目标,隔离个体
使用机器学习技术作为预测指标(目标3)。为了实现这些目标,我们将
利用由11,000多名青年组成的青少年大脑认知发展(ABCD)研究
参与者。ABCD提供神经成像、神经认知和环境测量的多个时间点
从9到10岁的年轻人开始,允许将高维数据合并到单个
框架。因此,所得到的样本提供了使用先进的定量方法的独特机会
包括结构方程建模、探索性因素分析和随机森林机器学习
强调是什么驱使年轻人在这个危险的发育期开始饮酒。这样做的结果是
该项目旨在为预防和干预EAI的研究提供信息,以最终推迟更多人开始饮酒
发育适宜的年龄。
英文摘要
Project Summary/Abstract
Recent initiatives from the National Institute on Alcohol Abuse and Alcoholism have focused on the prevention
of child and adolescent alcohol use. To address this, the proposed project focuses on identifying salient,
prospective predictors and inferred causes of early alcohol initiation (EAI) or the consumption of a full drink
containing alcohol before the age of 16. The aims of the proposed project will test current assumptions of
predictors of alcohol initiation (Aim 1a), compare a priori risk factors with novel, data-driven risk factors (Aim 1b),
infer causal relationships between factors and EAI (Aim 2), and, as an exploratory aim, isolate individual
measures as predictors using machine learning techniques (Aim 3). To accomplish these aims, we will be
leveraging the Adolescent Brain Cognitive Development (ABCD) study consisting of over 11,000 youth
participants. ABCD provides multiple time points of neuroimaging, neurocognitive, and environmental measures
starting when youth are 9-to-10-years-old allowing for the incorporation of high-dimensional data into a single
framework. Thus, the resulting sample provides a unique opportunity to use advanced quantitative methods
including structural equation modeling, exploratory factor analysis, and random forest machine learning to
highlight what drives youth to initiate alcohol use during this risky developmental period. The outcomes of this
project aim to inform research on prevention and intervention of EAI to ultimately delay alcohol initiation to more
developmentally appropriate ages.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
海外基金