Who is alcohol cue-reactive? A machine learning approach.

IF 2.2 4区 医学 Q3 SUBSTANCE ABUSE
Dylan E Kirsch, Kaitlin R McManus, Erica N Grodin, Steven J Nieto, Robert Miranda, Stephanie S O'Malley, Joseph P Schacht, Lara A Ray
{"title":"Who is alcohol cue-reactive? A machine learning approach.","authors":"Dylan E Kirsch, Kaitlin R McManus, Erica N Grodin, Steven J Nieto, Robert Miranda, Stephanie S O'Malley, Joseph P Schacht, Lara A Ray","doi":"10.1093/alcalc/agaf052","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>The alcohol cue-exposure paradigm is widely used in alcohol use disorder (AUD) research. Individuals with AUD exhibit considerable variability in their alcohol cue-reactivity, highlighting the need to identify characteristics that contribute to this heterogeneity. This study applied machine learning models to identify clinical and sociodemographic predictors of subjective alcohol cue-reactivity (ALCUrge).</p><p><strong>Methods: </strong>Individuals with AUD (N = 139; 83 M/56F) completed an alcohol cue-exposure paradigm and a battery of clinical and sociodemographic measures. ALCUrge (primary outcome variable) was assessed using the Alcohol Urge Questionnaire following alcohol cue-exposure. We implemented three machine learning models (Lasso regression, Ridge regression, Random Forest) to identify clinical and sociodemographic predictors of ALCUrge and compared model performance (i.e. predictive accuracy).</p><p><strong>Results: </strong>Lasso regression had the strongest predictive accuracy, with a Root Mean Square Error (RMSE) of 9.48, followed by Random Forest (RMSE = 9.95), and Ridge regression (RMSE = 10.40). All models outperformed chance-level prediction (null baseline model RMSE = 14.80). Top predictors of ALCUrge across multiple models were alcohol urge prior to cue-exposure, compulsive alcohol-related behaviors/thoughts, tonic alcohol craving, cigarette smoking status, and biological sex. Higher pre-cue exposure alcohol urge, more compulsive alcohol-related tendencies, greater tonic craving, and occasional cigarette use was associated with greater predicted ALCUrge, while being female was associated with lower predicted ALCUrge.</p><p><strong>Conclusion: </strong>This study advances our understanding of the phenotypic overlap in the compulsive aspects of tonic craving and phasic cue-induced alcohol urge, and offers insight into additional factors, such as biological sex and cigarette smoking, that may contribute to variability in alcohol cue-reactivity.</p>","PeriodicalId":7407,"journal":{"name":"Alcohol and alcoholism","volume":"60 5","pages":""},"PeriodicalIF":2.2000,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12368849/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Alcohol and alcoholism","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/alcalc/agaf052","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"SUBSTANCE ABUSE","Score":null,"Total":0}
引用次数: 0

Abstract

Background: The alcohol cue-exposure paradigm is widely used in alcohol use disorder (AUD) research. Individuals with AUD exhibit considerable variability in their alcohol cue-reactivity, highlighting the need to identify characteristics that contribute to this heterogeneity. This study applied machine learning models to identify clinical and sociodemographic predictors of subjective alcohol cue-reactivity (ALCUrge).

Methods: Individuals with AUD (N = 139; 83 M/56F) completed an alcohol cue-exposure paradigm and a battery of clinical and sociodemographic measures. ALCUrge (primary outcome variable) was assessed using the Alcohol Urge Questionnaire following alcohol cue-exposure. We implemented three machine learning models (Lasso regression, Ridge regression, Random Forest) to identify clinical and sociodemographic predictors of ALCUrge and compared model performance (i.e. predictive accuracy).

Results: Lasso regression had the strongest predictive accuracy, with a Root Mean Square Error (RMSE) of 9.48, followed by Random Forest (RMSE = 9.95), and Ridge regression (RMSE = 10.40). All models outperformed chance-level prediction (null baseline model RMSE = 14.80). Top predictors of ALCUrge across multiple models were alcohol urge prior to cue-exposure, compulsive alcohol-related behaviors/thoughts, tonic alcohol craving, cigarette smoking status, and biological sex. Higher pre-cue exposure alcohol urge, more compulsive alcohol-related tendencies, greater tonic craving, and occasional cigarette use was associated with greater predicted ALCUrge, while being female was associated with lower predicted ALCUrge.

Conclusion: This study advances our understanding of the phenotypic overlap in the compulsive aspects of tonic craving and phasic cue-induced alcohol urge, and offers insight into additional factors, such as biological sex and cigarette smoking, that may contribute to variability in alcohol cue-reactivity.

Abstract Image

Abstract Image

谁对酒精有反应?机器学习方法。
背景:酒精线索暴露范式在酒精使用障碍(AUD)研究中被广泛应用。AUD患者的酒精线索反应表现出相当大的差异,因此需要确定导致这种异质性的特征。本研究应用机器学习模型来确定主观酒精线索反应性(ALCUrge)的临床和社会人口学预测因子。方法:AUD患者(N = 139; 83 M/56F)完成了酒精提示暴露范式和一系列临床和社会人口学测量。ALCUrge(主要结局变量)在酒精提示暴露后使用酒精冲动问卷进行评估。我们实施了三种机器学习模型(Lasso回归,Ridge回归,Random Forest)来识别ALCUrge的临床和社会人口学预测因子,并比较模型性能(即预测准确性)。结果:Lasso回归预测准确率最高,均方根误差(RMSE)为9.48,其次是Random Forest (RMSE = 9.95)和Ridge回归(RMSE = 10.40)。所有模型都优于机会水平预测(零基线模型RMSE = 14.80)。在多个模型中,ALCUrge的主要预测因子是提示暴露前的酒精冲动、强迫性酒精相关行为/想法、补性酒精渴望、吸烟状况和生理性别。提示前接触酒精冲动、强迫性酒精相关倾向、更强的补品渴望和偶尔吸烟与较高的预测ALCUrge相关,而女性与较低的预测ALCUrge相关。结论:本研究促进了我们对补品渴望和相位提示诱导的酒精冲动的强迫性方面的表型重叠的理解,并提供了对可能导致酒精提示反应变异性的其他因素的见解,如生物性别和吸烟。
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
Alcohol and alcoholism
Alcohol and alcoholism 医学-药物滥用
CiteScore
4.70
自引率
3.60%
发文量
62
审稿时长
4-8 weeks
期刊介绍: About the Journal Alcohol and Alcoholism publishes papers on the biomedical, psychological, and sociological aspects of alcoholism and alcohol research, provided that they make a new and significant contribution to knowledge in the field. Papers include new results obtained experimentally, descriptions of new experimental (including clinical) methods of importance to the field of alcohol research and treatment, or new interpretations of existing results. Theoretical contributions are considered equally with papers dealing with experimental work provided that such theoretical contributions are not of a largely speculative or philosophical nature.
×
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