Absolute Risk Prediction for Cannabis Use Disorder in Adolescence and Early Adulthood Using Bayesian Machine Learning.

IF 3 3区 医学 Q2 SUBSTANCE ABUSE
Tingfang Wang, Joseph M Boden, Swati Biswas, Pankaj K Choudhary
{"title":"Absolute Risk Prediction for Cannabis Use Disorder in Adolescence and Early Adulthood Using Bayesian Machine Learning.","authors":"Tingfang Wang, Joseph M Boden, Swati Biswas, Pankaj K Choudhary","doi":"10.1111/dar.14098","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>Substance use disorders (SUD) have emerged as a pressing public health concern in the United States, with adolescent substance use often leading to SUDs in adulthood. Effective strategies are needed to stem this progression. To help fulfil this need, we developed a novel absolute risk prediction model for cannabis use disorder (CUD) for adolescents or young adults who use cannabis.</p><p><strong>Methods: </strong>We trained a Bayesian machine learning model that provides a personalised CUD absolute risk for adolescents or young adults who use cannabis with data from the National Longitudinal Study of Adolescent to Adult Health. Model performance was assessed using five-fold cross-validation (CV) with area under the curve (AUC) and ratio of the expected to observed number of cases (E/O). Independent validation of the final model was conducted using two datasets.</p><p><strong>Results: </strong>The proposed model has five risk factors: biological sex, delinquency, and scores on personality traits of conscientiousness, neuroticism and openness. For predicting CUD risk within 5 years of first cannabis use, AUC values for the training dataset and two validation datasets were 0.68, 0.64 and 0.75, respectively, and E/O values were 0.95, 0.98 and 1, respectively. This indicates good discrimination and calibration performance of the model.</p><p><strong>Discussion and conclusion: </strong>The proposed model can aid clinicians in assessing the risk of developing CUD among adolescents and young adults who use cannabis, enabling clinically appropriate interventions.</p>","PeriodicalId":11318,"journal":{"name":"Drug and alcohol review","volume":" ","pages":""},"PeriodicalIF":3.0000,"publicationDate":"2025-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Drug and alcohol review","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1111/dar.14098","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"SUBSTANCE ABUSE","Score":null,"Total":0}
引用次数: 0

Abstract

Introduction: Substance use disorders (SUD) have emerged as a pressing public health concern in the United States, with adolescent substance use often leading to SUDs in adulthood. Effective strategies are needed to stem this progression. To help fulfil this need, we developed a novel absolute risk prediction model for cannabis use disorder (CUD) for adolescents or young adults who use cannabis.

Methods: We trained a Bayesian machine learning model that provides a personalised CUD absolute risk for adolescents or young adults who use cannabis with data from the National Longitudinal Study of Adolescent to Adult Health. Model performance was assessed using five-fold cross-validation (CV) with area under the curve (AUC) and ratio of the expected to observed number of cases (E/O). Independent validation of the final model was conducted using two datasets.

Results: The proposed model has five risk factors: biological sex, delinquency, and scores on personality traits of conscientiousness, neuroticism and openness. For predicting CUD risk within 5 years of first cannabis use, AUC values for the training dataset and two validation datasets were 0.68, 0.64 and 0.75, respectively, and E/O values were 0.95, 0.98 and 1, respectively. This indicates good discrimination and calibration performance of the model.

Discussion and conclusion: The proposed model can aid clinicians in assessing the risk of developing CUD among adolescents and young adults who use cannabis, enabling clinically appropriate interventions.

使用贝叶斯机器学习预测青少年和成年早期大麻使用障碍的绝对风险。
物质使用障碍(SUD)在美国已成为一个紧迫的公共卫生问题,青少年物质使用通常导致成年后的SUD。需要有效的策略来阻止这种进展。为了帮助满足这一需求,我们为使用大麻的青少年或年轻人开发了一种新的大麻使用障碍(CUD)绝对风险预测模型。方法:我们训练了一个贝叶斯机器学习模型,该模型提供了使用大麻的青少年或年轻人的个性化CUD绝对风险,数据来自国家青少年到成人健康纵向研究。采用五重交叉验证(CV)、曲线下面积(AUC)和预期病例数与观察病例数之比(E/O)来评估模型的性能。使用两个数据集对最终模型进行独立验证。结果:该模型具有5个风险因子:生理性别、犯罪行为和责任心、神经质和开放性人格特征得分。对于预测首次使用大麻5年内的CUD风险,训练数据集和两个验证数据集的AUC值分别为0.68、0.64和0.75,E/O值分别为0.95、0.98和1。这表明该模型具有良好的判别和标定性能。讨论和结论:提出的模型可以帮助临床医生评估使用大麻的青少年和年轻人发生CUD的风险,使临床适当的干预成为可能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Drug and alcohol review
Drug and alcohol review SUBSTANCE ABUSE-
CiteScore
4.80
自引率
10.50%
发文量
151
期刊介绍: Drug and Alcohol Review is an international meeting ground for the views, expertise and experience of all those involved in studying alcohol, tobacco and drug problems. Contributors to the Journal examine and report on alcohol and drug use from a wide range of clinical, biomedical, epidemiological, psychological and sociological perspectives. Drug and Alcohol Review particularly encourages the submission of papers which have a harm reduction perspective. However, all philosophies will find a place in the Journal: the principal criterion for publication of papers is their quality.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信