Empirical Derivation and Prediction of Treatment Trajectories in Harmonized AUD Clinical Trial Datasets

IF 2.6 3区 医学 Q3 BIOCHEMISTRY & MOLECULAR BIOLOGY
Robert J. Kohler, Yasmin Zakiniaeiz, Terril L. Verplaetse, C. Leonardo Jimenez Chavez, MacKenzie R. Peltier, Hang Zhou, Sherry A. McKee, Walter Roberts
{"title":"Empirical Derivation and Prediction of Treatment Trajectories in Harmonized AUD Clinical Trial Datasets","authors":"Robert J. Kohler,&nbsp;Yasmin Zakiniaeiz,&nbsp;Terril L. Verplaetse,&nbsp;C. Leonardo Jimenez Chavez,&nbsp;MacKenzie R. Peltier,&nbsp;Hang Zhou,&nbsp;Sherry A. McKee,&nbsp;Walter Roberts","doi":"10.1111/adb.70069","DOIUrl":null,"url":null,"abstract":"<p>In clinical settings targeting alcohol use disorder (AUD), it is often unclear whether a treatment option may best suit a patient's clinical needs. Clinicians providing AUD treatment are often required to predict patients' responses to guide treatment decisions. Recently, machine learning approaches have been used as tools in precision medicine to help guide these clinical decisions. However, the extent of their clinical utility in populations undergoing treatment is largely unknown. Using data from four Phase 2 randomized clinical trials affiliated with the NIAAA Clinical Investigations Group and a Phase 3 trial sponsored by the NIAAA, we developed a machine learning model to predict treatment response phenotypes derived from clustering drinking rates at the end of treatment. Harmonized data included demographics and baseline data from biological and clinical assessments. Follow-up analyses were performed to characterize treatment response phenotypes. Three clusters corresponding to mild (M<sub>SDU</sub> = 1.3), moderate (M<sub>SDU</sub> = 6.70) and severe (M<sub>SDU</sub> = 15.3) alcohol consumption were identified from end-of-treatment drinking data. Performance of the tree-based classifier using out-of-sample test data was 71% with baseline drinking included and 61% without. Exploratory analyses revealed participants clustered as mild drinkers showed reductions in drinking across treatment (<i>M</i><sub><i>Difference</i></sub> = −0.731, SE = 0.114, <i>p</i> &lt; 0.001) whereas participants clustered as severe had escalation in use (<i>M</i><sub><i>Difference</i></sub> = 6.82, SE = 0.52, <i>p</i> &lt; 0.001). Although males drank more than females at baseline (<i>M</i><sub><i>Difference</i></sub> = 1.46, SE = 0.287, <i>p</i> &lt; 0.001), no significant differences in consumption emerged at the end of treatment. Findings from this work indicate that alcohol use derived from patterns of consumption at the end of treatment maps onto unique treatment response trajectories for mild and severe forms of AUD. Furthermore, the identified clusters revealed sex-specific differences in alcohol consumption patterns across different phases of treatment. Overall, this highlights the utility of computational methods for deriving clinically meaningful AUD-related phenotypes across multiple studies, each with different treatments and participant characteristics.</p>","PeriodicalId":7289,"journal":{"name":"Addiction Biology","volume":"30 7","pages":""},"PeriodicalIF":2.6000,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/adb.70069","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Addiction Biology","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/adb.70069","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"BIOCHEMISTRY & MOLECULAR BIOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

In clinical settings targeting alcohol use disorder (AUD), it is often unclear whether a treatment option may best suit a patient's clinical needs. Clinicians providing AUD treatment are often required to predict patients' responses to guide treatment decisions. Recently, machine learning approaches have been used as tools in precision medicine to help guide these clinical decisions. However, the extent of their clinical utility in populations undergoing treatment is largely unknown. Using data from four Phase 2 randomized clinical trials affiliated with the NIAAA Clinical Investigations Group and a Phase 3 trial sponsored by the NIAAA, we developed a machine learning model to predict treatment response phenotypes derived from clustering drinking rates at the end of treatment. Harmonized data included demographics and baseline data from biological and clinical assessments. Follow-up analyses were performed to characterize treatment response phenotypes. Three clusters corresponding to mild (MSDU = 1.3), moderate (MSDU = 6.70) and severe (MSDU = 15.3) alcohol consumption were identified from end-of-treatment drinking data. Performance of the tree-based classifier using out-of-sample test data was 71% with baseline drinking included and 61% without. Exploratory analyses revealed participants clustered as mild drinkers showed reductions in drinking across treatment (MDifference = −0.731, SE = 0.114, p < 0.001) whereas participants clustered as severe had escalation in use (MDifference = 6.82, SE = 0.52, p < 0.001). Although males drank more than females at baseline (MDifference = 1.46, SE = 0.287, p < 0.001), no significant differences in consumption emerged at the end of treatment. Findings from this work indicate that alcohol use derived from patterns of consumption at the end of treatment maps onto unique treatment response trajectories for mild and severe forms of AUD. Furthermore, the identified clusters revealed sex-specific differences in alcohol consumption patterns across different phases of treatment. Overall, this highlights the utility of computational methods for deriving clinically meaningful AUD-related phenotypes across multiple studies, each with different treatments and participant characteristics.

Abstract Image

协调AUD临床试验数据集中治疗轨迹的经验推导和预测
在针对酒精使用障碍(AUD)的临床设置中,通常不清楚治疗方案是否最适合患者的临床需求。提供AUD治疗的临床医生通常需要预测患者的反应来指导治疗决策。最近,机器学习方法已被用作精准医学的工具,以帮助指导这些临床决策。然而,它们在接受治疗人群中的临床应用程度在很大程度上是未知的。利用隶属于NIAAA临床调查小组的四项2期随机临床试验和NIAAA赞助的3期试验的数据,我们开发了一个机器学习模型来预测治疗结束时聚类饮酒率得出的治疗反应表型。统一的数据包括来自生物和临床评估的人口统计数据和基线数据。进行随访分析以表征治疗反应表型。从治疗结束的饮酒数据中确定了轻度(MSDU = 1.3)、中度(MSDU = 6.70)和重度(MSDU = 15.3)饮酒的三个集群。使用样本外测试数据的基于树的分类器的性能在包括基线饮酒的情况下为71%,在不包括基线饮酒的情况下为61%。探索性分析显示,轻度饮酒者在治疗期间饮酒量减少(MDifference = - 0.731, SE = 0.114, p < 0.001),重度饮酒者饮酒量增加(MDifference = 6.82, SE = 0.52, p < 0.001)。虽然男性在基线时的饮酒量高于女性(MDifference = 1.46, SE = 0.287, p < 0.001),但在治疗结束时,饮酒量没有显著差异。这项工作的发现表明,治疗结束时的饮酒模式衍生出的酒精使用映射到轻度和重度AUD形式的独特治疗反应轨迹。此外,确定的集群揭示了不同治疗阶段酒精消费模式的性别差异。总的来说,这突出了计算方法在多个研究中获得具有临床意义的aud相关表型的实用性,每个研究都有不同的治疗方法和参与者特征。
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
Addiction Biology
Addiction Biology 生物-生化与分子生物学
CiteScore
8.10
自引率
2.90%
发文量
118
审稿时长
6-12 weeks
期刊介绍: Addiction Biology is focused on neuroscience contributions and it aims to advance our understanding of the action of drugs of abuse and addictive processes. Papers are accepted in both animal experimentation or clinical research. The content is geared towards behavioral, molecular, genetic, biochemical, neuro-biological and pharmacology aspects of these fields. Addiction Biology includes peer-reviewed original research reports and reviews. Addiction Biology is published on behalf of the Society for the Study of Addiction to Alcohol and other Drugs (SSA). Members of the Society for the Study of Addiction receive the Journal as part of their annual membership subscription.
×
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