Using machine learning to predict heavy drinking during outpatient alcohol treatment.
Using machine learning to predict heavy drinking during outpatient alcohol treatment.
复制标题
DOI：
10.1111/acer.14802
复制
发表时间：
2022-04
期刊：
影响因子：
--
通讯作者：
McKee, Sherry
中科院分区：
文献类型：
--
作者：
Roberts, Walter;Zhao, Yize;Verplaetse, Terril;Moore, Kelly E.;Peltier, MacKenzie R.;Burke, Catherine;Zakiniaeiz, Yasmin;McKee, Sherry
准确的临床预测支持酒精使用障碍（AUD）和其他精神疾病的有效治疗。传统的统计技术已经确定了与治疗结果相关的患者特征;然而，较少的工作集中在系统地利用这些关联来创建最佳预测模型。目前的研究展示了机器学习如何用于预测完成门诊AUD治疗的患者的临床结果。我们使用来自联合收割机多中心临床试验（n = 1，383）的数据来开发和测试预测模型。我们确定了3个优先预测目标，包括1）治疗第一个月期间的大量饮酒，2）治疗最后一个月期间的大量饮酒，以及3）每周/每两周治疗之间的大量饮酒。使用随机森林算法生成模型。我们使用“leave sites out”分区来外部验证未包括在模型训练中的试验中心中的模型。分层模型开发用于检验预测特征相对重要性的性别差异。预测治疗第一个月和最后一个月重度饮酒的模型显示，内部交叉验证曲线下面积（AUC）评分范围为0.67至0.74。在外部验证中，使用保留研究中心的数据，AUC相当（AUC范围= 0.69 - 0.72）。在大量饮酒期间预测的模型在内部交叉验证（AUC = 0.89）和外部测试样本（AUC范围= 0.80 - 0.87）中显示出很强的分类准确性。分层分析发现，最佳功能集的性别差异很大。机器学习技术可以使用常规收集的临床数据预测酒精使用治疗结果。这种技术有可能大大提高临床预测的准确性，而不需要昂贵的或侵入性的评估技术。需要更多的研究来了解如何最好地部署这些模型。
Accurate clinical prediction supports effective treatment of alcohol use disorder (AUD) and other psychiatric disorders. Traditional statistical techniques have identified patient characteristics associated with treatment outcomes; however, less work has focused on systematically leveraging these associations to create optimal predictive models. The current study demonstrates how machine learning can be used to predict clinical outcomes in people completing outpatient AUD treatment. We used data from the COMBINE multisite clinical trial (n = 1,383) to develop and test predictive models. We identified 3 priority prediction targets, including 1) heavy drinking during the first month of treatment, 2) heavy drinking during the last month of treatment, and 3) heavy drinking in-between weekly/bi-weekly sessions. Models were generated using the random forest algorithm. We used “leave sites out” partitioning to externally validate the models in trial sites that were not included in the model training. Stratified model development was used to test for sex differences in the relative importance of predictive features. Models predicting heavy alcohol use during the first and last months of treatment showed internal cross validation area under the curve (AUC) scores ranging from 0.67 to 0.74. AUC was comparable in the external validation using data from held out sites (AUC range = 0.69 – 0.72). The model predicting between session heavy drinking showed strong classification accuracy in internal cross-validation (AUC = 0.89) and external test samples (AUC range = 0.80 – 0.87). Stratified analyses found substantial sex differences in optimal feature sets. Machine learning techniques can predict alcohol use treatment outcomes using routinely collected clinical data. This technique has potential to greatly improve clinical prediction accuracy without requiring expensive or invasive assessment techniques. More research is needed to understand how to best deploy these models.
登录
查看更多内容
影响因子：
4.2
作者：
Chiappetta, Viviana;Garcia-Rodriguez, Olaya;Blanco, Carlos
通讯作者：
Blanco, Carlos
影响因子：
10.7
作者：
Davis, Jonathan M. V.;Heller, Sara B.
通讯作者：
Heller, Sara B.
影响因子：
64.3
作者：
Chekroud, Adam Mourad;Zotti, Ryan Joseph;Corlett, Philip Robert
通讯作者：
Corlett, Philip Robert
影响因子：
5.8
作者：
Kursa, Miron B.;Rudnicki, Witold R.
通讯作者：
Rudnicki, Witold R.
DOI：
10.1093/bioinformatics/btr204
发表时间：
2011-07-01
期刊：
Bioinformatics (Oxford, England)
影响因子：
--
作者：
Li L;Rakitsch B;Borgwardt K
通讯作者：
Borgwardt K