Adaptive Interventions for Problem Drinkers

描述(由申请人提供)：问题饮酒者(PD)代表了大约3200万美国人中的大多数人患有酒精问题，这些问题的严重程度从过度饮酒和偶尔经历负面后果到中度AD和心理社会功能正常的人。PDS可以受益于主流医疗保健可以提供的相对简短的治疗，但只有不到5%的人接受了这种治疗。此外，帕金森病的治疗只有一定的效果，令人惊讶的是，缺乏指导帕金森病治疗选择的实证研究。适应性干预(AI)是一种新的治疗开发方法，在提高疗效和促进主流医疗保健采用EBPS方面可能比固定治疗具有显著优势。在过去的十年中，人工智能开发方法取得了重要进展，包括顺序多任务随机试验(SMART)和控制工程(CE)设计。这些进展已经在治疗其他慢性病方面取得了重要发现，但才刚刚开始应用于澳门氏症。本研究建议将SMART、CE和生态瞬时评估相结合，开发一种可用于主流医疗保健的PD人工智能。如果研究目标得以实现，一套经验派生的决策支持工具将被 创建的目的是指导澳大利亚的医疗保健，类似于其他慢性病的现有工具。此外，还将获得有关AUD的MOBC的新知识，以指导未来的AUD治疗研究。最后，将在利用传感器技术、高等数学和工程学的显著进步的方法上取得重要进展，以创建一种新型的定制、近实时反馈、适应性行为疗法

DESCRIPTION (provided by applicant): Problem drinkers (PDs) represent a majority of the estimated 32 million Americans with alcohol problems that spans a spectrum of severity from individuals who drink excessively and experience of occasional negative consequences to those with moderate AD and intact psychosocial functioning. PDs can benefit from relatively brief treatment that could be delivered in mainstream healthcare, but less than 5% receive such care. In addition, PD treatment is only modestly effective, and there is a surprising absence of empirical research to guide PD treatment selection. Adaptive Interventions (AI) are a novel approach to treatment development that may have significant advantages over fixed treatments in improving efficacy and fostering adoption of EBPs in mainstream healthcare. Over the last decade, important advances have been made in AI development methods including Sequential Multiple Assignment Randomized Trials (SMART) and control engineering (CE) designs. These advances have yielded important discoveries in the treatment of other chronic illnesses but are just beginning to be applied to AUD. This study proposes to combine SMART, CE, and ecological momentary assessment to develop an AI for PD that can be used in mainstream healthcare. If study aims are achieved, a set of empirically-derived decision support tools will be created to guide AUD care similar to tools that exist for other chronic diseases. In addition, new knowledge will be gained about MOBC of AUD that can guide future AUD treatment research. Finally, important progress will be made in methods that capitalize on the remarkable advances in sensor technologies, advanced mathematics, and engineering to create a new type of tailored, near-real time feedback, adaptive behavior therapies