SCH: INT: Collaborative Research: Monitoring and Modeling Family Eating Dynamics (M2 FED): Reducing Obesity Without Focusing on Diet and Activity

该项目由美国国家科学基金会和美国国立卫生研究院联合征集资金，名为“智能互联健康”(SCH)，旨在加快创新方法的开发和使用，以支持全民亟需的医疗保健转型。肥胖流行是最近心脏病、糖尿病、癌症和其他疾病增加的主要原因，这些疾病给医疗保健和公共卫生带来了难以承受的压力。主要的行为原因之一，即饮食摄入，是一种科学在理解上几乎没有成功的行为，更不用说影响了。遥感的最新进展为跟踪人类行为提供了一个新的范式，但直接关注饮食和活动的肥胖相关努力不仅受到行为跟踪(特别是饮食摄入量)的准确性的阻碍，而且缺乏个性化的及时、适应性干预(JITAI)的行为理论和动态模型。目前的行为科学表明，家庭饮食动态(FED)具有很高的潜在影响儿童和父母的饮食摄入量和肥胖率。技术研究和行为科学研究的融合创造了机会，将原位肥胖研究和干预的重点从被证明难以监测、建模和修改(例如，吃了什么和多少)的行为转移到家庭用餐时间和家庭食物环境(例如，谁在吃饭，何时、何地、与谁在一起，人际压力)，通过遥感为监测和建模(M2)行为提供机会，并通过个性化、适应性、实时反馈实现成功的行为矫正。该项目提出了M2FED，这是一个由家庭信标、无线和可穿戴传感器组成的集成系统，以及收集同步的实时美联储数据的智能手机，这些数据将被用来迭代地开发基于这些数据的动态、情境化的美联储系统模型。迭代开发这些模型的技术、表意模型和技术可以指导未来的JITAI，从而对饮食和最终肥胖产生下游的积极影响。该项目汇集了行为科学家、系统科学家、肥胖专家、计算机科学家和电气工程师，以解决远程、连续数据捕获的基本挑战，以用于肥胖预防和治疗的实时行为建模。行为科学家传统上无法获得实时数据和动态模型，而工程师也没有专业知识来确定要监控和建模什么，或者提供什么反馈。该项目将免费的专业知识结合在一起，开发出一种截然不同的儿童肥胖方法，专注于行为，即饮食而不是饮食，可以更准确地监测和建模，并具有更大的积极和长期修正的潜力。实现M2FED系统的基本技术研究挑战包括独特的个人家庭定位、进食检测、在混响环境中的谈话压力和情绪评估，以及包括整个家庭系统本身的异类传感和通信系统的系统框架。基本的行为研究挑战包括基于对FED状态的过去和正在进行的观察以及对FED产生时间和因果影响的内部和人际状态以及事件对FED进行实时建模。虽然这个项目是在肥胖/FED关系(这本身有可能对人类健康和医疗保健成本产生全面影响)的背景下进行的，但该项目也概括了一个框架，包括一个基于证据的系统和一个实验平台，该平台扩展到儿童肥胖和行为矫正以外的系统和应用。这项工作的多学科性质还提供了新的外展和教育机会，向公众提供信息(并从中获得信息)，并培养一支更有能力应对基本的以人类行为为中心的健康管理和健康维护挑战的劳动力队伍。

This project is funded under a joint solicitation between the National Science Foundation and the National Institutes of Health, named "Smart and Connected Health" (SCH), which aims to accelerate the development and use of innovative approaches that would support the much needed transformation of healthcare across the entire population. The obesity epidemic is the primary cause of recent increases in heart disease, diabetes, cancer, and other diseases that place an untenable strain on healthcare and public health. One of the primary behavioral causes, i.e. dietary intake, is a behavior that science has had little success in understanding, much less affecting. Recent advances in remote sensing have provided a new paradigm for tracking human behavior, but obesity-related efforts focused directly on diet and activity have been hampered by not only the accuracy of behavior tracking (especially dietary intake) but also the lack of behavioral theories and dynamic models for personalized just-in-time, adaptive interventions (JITAIs). Current behavioral science suggests that family eating dynamics (FED) have high potential to impact child and parent dietary intake and obesity rates. The confluence of technology research and behavioral science research creates the opportunity to change the focus of in situ obesity research and intervention from behaviors that have proven difficult to monitor, model, and modify (e.g., what and how much is being eaten) to the family mealtime and home food environment (e.g., who is eating, when, where, with whom, interpersonal stress), providing opportunities for monitoring and modeling (M2) behavior via remote sensing, and the potential for successful behavior modification via personalized, adaptable, real-time feedback.This project proposes M2FED, an integrated system of in-home beacons, wireless and wearable sensors, and smartphones that collects synchronized real-time FED data that will be used to iteratively develop dynamic, contextualized FED systems models based on that data. The technology, ideographic models, and techniques to iteratively develop those models can guide future JITAIs and thus have a downstream positive impact on diet and ultimately obesity. The project brings together behavioral scientists, system scientists, obesity experts, computer scientists, and electrical engineers to address fundamental challenges of remote, continuous data capture for real-time behavior modeling for obesity prevention and treatment. Behavioral scientists traditionally have not had access to real-time data and dynamic models, while engineers have not had the expertise to identify what to monitor and model or what feedback to provide. This project connects complimentary expertise to develop a dramatically different approach to childhood obesity, focusing on behaviors, i.e. FED rather than diet, that can be more accurately monitored and modeled and have greater potential for positive and long-term modification. Fundamental technology research challenges in realizing the M2FED system include unique individual in-home localization, eating detection, conversation stress and mood assessment in reverberant environments, and a system-of-systems framework that includes heterogeneous sensing and communication systems across the family system itself. Fundamental behavioral research challenges include real-time modeling of FED based on past and ongoing observations of FED states and intra- and interpersonal states and events that create temporal and causal impact on FED. While this project is performed within the context of the obesity/FED relationship (which itself has the potential for sweeping impacts on human health and healthcare costs), the project also generalizes a framework, including both an evidence-based system and an experimental platform that extends to systems and applications beyond childhood obesity and behavior modification. The multidisciplinary nature of this work also provides new outreach and educational opportunities, informing (and being informed by) the public and preparing a workforce that is better equipped to address the fundamental human-behavior-centric challenges of health management and wellness preservation.