A clinician-in-the-loop smart home to support health monitoring and intervention for chronic conditions

项目概要/摘要 世界人口正在老龄化，患有慢性疾病的老年人数量不断增加 我们社会必须应对的挑战。虽然智能环境的想法现已成为现实，但仍存在差距 我们了解如何扩展智能家居技术以在复杂环境中使用以及如何使用机器 学习和活动学习技术来设计自动化健康评估和干预策略。 该项目的长期目标是通过以下方式改善人类健康并影响医疗保健服务的提供： 开发有助于健康监测和干预的智能环境。此举的首要目标 该应用程序的目的是设计一个“循环中的临床医生”智能家居，使个人能够管理自己的慢性病 通过自动化健康监测、评估和干预影响评估来了解健康状况。 基于我们之前的工作，该方法将生成描述个人行为的分析 使用智能家居、智能手机和活动学习的日常活动（目标 1）。我们训练有素的临床医生将使用 分析以执行健康评估和健康事件检测（目标 2）。此外，我们还将介绍 大脑健康干预措施，支持大脑健康的可持续改善（目标 3）。最后，我们训练 从临床观察到自动评估健康和干预的机器学习算法 影响（目标 4）。这些技术的使用预计将改善和扩展功能健康和 老年人的福祉，带来更积极主动和预防性的医疗保健，并减轻护理人员的负担 健康监测和援助。通过了解影响及时遵守的情境因素， 可以增加依从情况。该方法具有创新性，因为它将探索和验证新的方法 基于临床事实的活动学习和健康评估的机器学习技术。这些 贡献是重大的，因为它们可以通过以下方式扩展我们老龄化社会的健康自我管理 主动医疗保健和实时干预，减轻护理人员的情感和经济负担 和社会。考虑到疗养院护理费用、家庭护理的影响以及人们的重要性 注重呆在家里，增加功能独立性的技术，从而支持就地养老 提高个人及其护理人员的生活质量对双方都具有重要价值 个人和社会。

PROJECT SUMMARY/ABSTRACT The world's population is aging and the increasing number of older adults with chronic health conditions is a challenge our society must address. While the idea of smart environments is now a reality, there remain gaps in our knowledge about how to scale smart homes technologies for use in complex settings and to use machine learning and activity learning technologies to design automated health assessment and intervention strategies. The long-term objective of this project is to improve human health and impact health care delivery by developing smart environments that aid with health monitoring and intervention. The primary objective of this application is to design a “clinician in the loop” smart home to empower individuals in managing their chronic health conditions by automating health monitoring, assessment, and evaluation of intervention impact. Building on our prior work, the approach will be to generate analytics describing an individual's behavior routine using smart homes, smart phones, and activity learning (Aim 1). Our trained clinicians will use the analytics to perform health assessment and detection of health events (Aim 2). In addition, we will introduce brain health interventions to support sustainable improvement of brain health (Aim 3). Finally, we train machine learning algorithms from the clinical observations to automate assessment of health and intervention impact (Aim 4). The use of these technologies is expected to improve and extend the functional health and wellbeing of older adults, lead to more proactive and preventative health care, and reduce the caregiver burden of health monitoring and assistance. By understanding situational factors that impact prompt adherence, adherence situations can be increased. The approach is innovative because it will explore and validate new machine learning techniques for activity learning and health assessment based on clinical ground truth. These contributions are significant because they can extend the health self-management of our aging society through proactive health care and real-time intervention, and reduce the emotional and financial burden for caregivers and society. Given nursing home care costs, the impact of family-based care, and the importance that people place on staying at home, technologies that increase functional independence and thus support aging in place while improving quality of life for both individuals and their caregivers are of significant value to both individuals and society.