Implementing and Scaling the STEADI Fall Prevention Algorithm Using a Conversational Relational Agent for Community-Dwelling Older Adults with and without Mild Cognitive Impairment (MCI).

摘要 跌倒严重威胁美国老年人的健康和福祉，特别是那些认知能力较弱的人 认知在步态中扮演的角色导致的损害(MCI)和痴呆症。跌倒是受伤的主要原因- 美国人≥65岁(老年人)的相关死亡，以及年龄调整后的死亡率 瀑布越来越多。每年有三分之一的老年人摔倒，超过300万人因跌倒而在医院接受治疗 每年都会受伤。那些跌倒一次的人再次跌倒的可能性是其他人的两到三倍，而患有 MCI/痴呆症的发病率是认知健康老年人的两到三倍。有效的预防跌倒可能 大大减少老年人的残疾、住院和丧失独立性，并改善他们的 生活质量。由疾病中心发起的STEADI(阻止老年人意外、死亡和伤害)倡议 控制和预防(CDC)结合了跌倒风险筛查、评估和干预，基于临床 美国和英国老年病学会的实践指南(2010)。作为一个全面、多因素的 干预，Steadi可以降低跌倒的风险和比率，但使用传统的 传播模式(笔墨、面对面访问、人类遵守情况监测和护理协调) 需要广泛的基础设施和人力资源，才能显著影响处于危险中的人口。 由Care.Coach公司(加利福尼亚州米尔布雷)与临床、学术、 和社区合作伙伴，旨在测试数字Steadi干预的可行性和有效性，包括 循证锻炼计划(OTAGO)，为老年人提供MCI力量和平衡 在家中进行舒适的训练，远程监测他们的步态，作为跌倒风险和 拒绝。为了远程交付Steadi，Care.Coach将采用其已经成功的对话技术 具有虚拟健康助手(头像)的平台，用于筛查社区居住的老年人是否有跌倒风险和修改- 危险因素，并使用有效的、个性化的运动养生和指导计划进行干预 随着时间的推移，学习和适应。数字干预在人工智能(AI)的帮助下执行，并且是 由全天候的人类员工团队监督，他们远程管理化身、提供陪伴并上报 根据需要提供给护理提供者。交付内容是经过严格测试、可扩展的数字Steadi干预选项- 可在家中进行持续的跌倒风险监控、定制干预和锻炼以及及时护理协调- 与卫生专业人员进行沟通。这项工作完成后，该方案将可供国家实施-- 通过现有客户和新客户进行推广和商业化。

ABSTRACT Falls are a serious threat to the health and well-being of older Americans, especially those with mild cognitive impairment (MCI) and dementia due to the role cognition plays in gait. Falls are the leading cause of injury- related deaths among Americans ≥ 65 years of age (older adults), and the age-adjusted rate of deaths from falls is increasing. One in three older adults falls each year, and over 3 million are treated in hospitals for fall injuries every year. Those who fall once are two to three times more likely to fall again, and older adults with MCI/dementia fall two to three times more than cognitive healthy older adults. Effective fall prevention could substantially reduce disability, hospitalizations, and loss of independence in older adults, and improve their quality of life. The STEADI (Stopping Elderly Accidents, Deaths & Injuries) Initiative by the Centers for Disease Control and Prevention (CDC) combines fall risk screening, assessments and intervention based on the clinical practice guidelines (2010) by the American and British Geriatrics Societies. As a comprehensive, multifactorial intervention, STEADI can reduce the risk and rate of falling, but is challenging to implement using traditional dissemination models (pen and ink, in-person visits, human adherence monitoring and care coordination) that require extensive infrastructure and human resources to significantly impact the population at risk. The proposed Fast-Track SBIR by care.coach corporation (Millbrae, CA) in partnership with clinical, academic, and community partners, aims to test the feasibility and efficacy of a digital STEADI intervention including an evidence-based exercise program (Otago) to offer older adults with and without MCI strength and balance training in the comfort of their home, and remotely monitor their gait as an early clinical indicator of fall risk and decline. To deliver STEADI remotely, care.coach will adapt its already successful conversational technology platform with virtual health assistant (avatar) to screen community-dwelling older adults for fall risk and modifia- ble risk factors, and to intervene using an effective, personalized exercise regimen and coaching program that learns and adapts over time. The digital intervention is executed with the help of artificial intelligence (AI) and is overseen by a 24x7 team of human staff who manage the avatars remotely, offer companionship, and escalate as needed to care providers. The deliverable is a rigorously tested, scalable digital STEADI intervention opti- mized for ongoing fall risk monitoring at home, customized intervention and exercise, and timely care coordina- tion with health professionals. Upon completion of this work, the program will be ready for national implementa- tion and commercialization via existing and new customers.