Demiris George, Harrison Sean, Sefcik Justine, Skubic Marjorie, Richmond Therese S, Hodgson Nancy A
Department of Biobehavioral Health Sciences, School of Nursing, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
College of Nursing and Health Professions, Drexel University, Philadelphia, Pennsylvania, USA.
J Gerontol A Biol Sci Med Sci. 2025 May 5;80(6). doi: 10.1093/gerona/glaf043.
Falls and fall-related injuries are significant public health issues for adults 65 years of age and older. The annual direct medical costs in the United States as a result of falls are estimated to exceed $50 billion, and this estimate does not include the indirect costs of disability, dependence, and decreased quality of life. This project targets community-dwelling older adults (OA) with mild cognitive impairment (MCI) who are socially vulnerable and thus at high risk for falling.
We have developed an innovative technology-supported nursing-driven intervention called Sense4Safety to (a) identify escalating risk for falls real time through in-home passive sensor monitoring (including depth sensors); (b) employ machine learning to inform individualized alerts for fall risk; and (c) link "at risk" socially vulnerable OA with a coach who guides them in implementing evidence-based individualized plans to reduce fall risk. The purpose of this study was to assess the feasibility and acceptability of the Sense4Safety intervention through participant interviews.
We recruited a cohort of 11 low-income OA with MCI who received the intervention for 3 months. Our study findings indicate the overall feasibility of the intervention with most participants (n = 9; 82%) having confidence in the passive monitoring system to effectively predict fall risk and generate actionable and tailored information that informs educational and exercise components.
Passive sensing technologies can introduce acceptable platforms for fall prevention for community-dwelling OA with MCI.
跌倒及与跌倒相关的损伤是65岁及以上成年人面临的重大公共卫生问题。据估计，美国每年因跌倒产生的直接医疗费用超过500亿美元，而这一估计尚不包括残疾、依赖和生活质量下降等间接成本。该项目针对的是社区居住的患有轻度认知障碍（MCI）的老年人（OA），他们在社会上较为脆弱，因此跌倒风险较高。
我们开发了一种创新的、由技术支持且以护理为主导的干预措施，称为“安全感知”（Sense4Safety），以（a）通过家庭被动传感器监测（包括深度传感器）实时识别不断升级的跌倒风险；（b）利用机器学习为跌倒风险提供个性化警报；（c）将处于“风险中”的社会脆弱OA与一名教练联系起来，该教练指导他们实施基于证据的个性化计划以降低跌倒风险。本研究的目的是通过参与者访谈评估“安全感知”干预措施的可行性和可接受性。
我们招募了11名患有MCI的低收入OA组成一个队列，他们接受了为期3个月的干预。我们的研究结果表明该干预措施总体可行，大多数参与者（n = 9；82%）对被动监测系统有信心，认为其能有效预测跌倒风险并生成可操作且量身定制的信息，为教育和锻炼部分提供依据。
被动传感技术可为社区居住的患有MCI的OA引入可接受的预防跌倒平台。
