Predictive modeling of addiction lapses in a mobile health application
Predictive modeling of addiction lapses in a mobile health application
复制标题
DOI：
10.1016/j.jsat.2013.08.004
复制
发表时间：
2014-01-01
影响因子：
3.9
通讯作者：
Gustafson, David H.
中科院分区：
文献类型：
--
作者：
Chih, Ming-Yuan;Patton, Timothy;Gustafson, David H.
酗酒的慢性复发性导致了巨大的个人，家庭和社会成本。成瘾综合健康增强支持系统（A-CHESS）是一款旨在减少复发的智能手机应用程序。为了向未来一周内有失误风险的患者提供有针对性的支持，使用来自152名最近完成住院治疗的酒精依赖者的2，934份每周调查（称为每周检查）的回复构建了预测此类事件的贝叶斯网络模型。“每周报到”是一项自我监察服务，透过A-CHESS提供，以追踪病人的康复进度。该模型显示出良好的预测性，在10倍交叉验证和外部验证中，受试者工作特征曲线下面积分别为0.829和0.912。灵敏度/特异性表有助于在实践中应用模型所需的权衡决策。这项研究使我们更接近提供失效预测的目标，以便患者可以获得更有针对性和及时的支持。(C)2013 Elsevier Inc. All rights reserved.
The chronically relapsing nature of alcoholism leads to substantial personal, family, and societal costs. Addiction-comprehensive health enhancement support system (A-CHESS) is a smartphone application that aims to reduce relapse. To offer targeted support to patients who are at risk of lapses within the coming week, a Bayesian network model to predict such events was constructed using responses on 2,934 weekly surveys (called the Weekly Check-in) from 152 alcohol-dependent individuals who recently completed residential treatment. The Weekly Check-in is a self-monitoring service, provided in A-CHESS, to track patients' recovery progress. The model showed good predictability, with the area under receiver operating characteristic curve of 0.829 in the 10-fold cross-validation and 0.912 in the external validation. The sensitivity/specificity table assists the tradeoff decisions necessary to apply the model in practice. This study moves us closer to the goal of providing lapse prediction so that patients might receive more targeted and timely support. (C) 2013 Elsevier Inc. All rights reserved.