Goldstein Stephanie P, Thomas J Graham, Foster Gary D, Turner-McGrievy Gabrielle, Butryn Meghan L, Herbert James D, Martin Gerald J, Forman Evan M
The Warren Alpert Medical School of Brown University, USA.
WW (Weight Watchers), USA; University of Pennsylvania, USA.
Health Informatics J. 2020 Dec;26(4):2315-2331. doi: 10.1177/1460458220902330. Epub 2020 Feb 6.
Suboptimal weight losses are partially attributable to lapses from a prescribed diet. We developed an app (OnTrack) that uses ecological momentary assessment to measure dietary lapses and relevant lapse triggers and provides personalized intervention using machine learning. Initially, tension between user burden and complete data was resolved by presenting a subset of lapse trigger questions per ecological momentary assessment survey. However, this produced substantial missing data, which could reduce algorithm performance. We examined the effect of more questions per ecological momentary assessment survey on algorithm performance, app utilization, and behavioral outcomes. Participants with overweight/obesity ( = 121) used a 10-week mobile weight loss program and were randomized to OnTrack-short (i.e. 8 questions/survey) or OnTrack-long (i.e. 17 questions/survey). Additional questions reduced ecological momentary assessment adherence; however, increased data completeness improved algorithm performance. There were no differences in perceived effectiveness, app utilization, or behavioral outcomes. Minimal differences in utilization and perceived effectiveness likely contributed to similar behavioral outcomes across various conditions.
减肥效果欠佳部分归因于偏离规定饮食。我们开发了一款应用程序（OnTrack），它利用生态瞬时评估来衡量饮食偏离情况及相关的偏离触发因素，并使用机器学习提供个性化干预。最初，通过在每次生态瞬时评估调查中呈现一部分偏离触发因素问题，解决了用户负担与完整数据之间的矛盾。然而，这产生了大量缺失数据，可能会降低算法性能。我们研究了每次生态瞬时评估调查增加问题数量对算法性能、应用程序使用情况和行为结果的影响。超重/肥胖参与者（=121）使用了一个为期10周的移动减肥计划，并被随机分为OnTrack-简短版（即每次调查8个问题）或OnTrack-完整版（即每次调查17个问题）。额外的问题降低了生态瞬时评估的依从性；然而，数据完整性的提高改善了算法性能。在感知有效性、应用程序使用情况或行为结果方面没有差异。使用情况和感知有效性的微小差异可能导致了不同条件下类似的行为结果。
