S W M Groeneveld, T Dekkers, Jewc van Gemert-Pijnen, R M Verdaasdonk, T J Verveda, R Witteveen, H van Os-Medendorp, M E M den Ouden
{"title":"Understanding the Factors that Influence the Implementation of AI-Driven Lifestyle Monitoring in Long-Term Care for Older Adults.","authors":"S W M Groeneveld, T Dekkers, Jewc van Gemert-Pijnen, R M Verdaasdonk, T J Verveda, R Witteveen, H van Os-Medendorp, M E M den Ouden","doi":"10.1093/geront/gnaf230","DOIUrl":null,"url":null,"abstract":"<p><strong>Background and objectives: </strong>AI-driven lifestyle monitoring systems collect data from ambient, motion, contact, light, and physiological sensors placed in the home, enabling AI algorithms to identify daily routines and detect deviations to support older adults \"aging in place.\" Despite its potential to support several challenges in long-term care for older adults, implementation remains limited. This study explored the facilitators and barriers to implementing AI-driven lifestyle monitoring in long-term care for older adults, as perceived by formal and informal caregivers, as well as management, in both an adopting and non-adopting healthcare organization.</p><p><strong>Research design and methods: </strong>A qualitative interview study using semi-structured interviews was conducted with 22 participants (5 informal caregivers, 10 formal caregivers, and 7 participants in a management position) from two long-term care organizations. Reflexive thematic analysis, guided by the nonadoption, abandonment, scale-up, spread, and sustainability (NASSS) framework, structured findings into facilitators and barriers.</p><p><strong>Results: </strong>12 facilitators and 16 barriers were identified, highlighting AI-driven lifestyle monitoring as a valuable, patient-centred, and unobtrusive tool enhancing care efficiency and caregiver reassurance. However, barriers such as privacy concerns, notification overload, training needs, and organizational alignment must be addressed. Contextual factors, including regulations, partnerships, and financial considerations, further influence implementation.</p><p><strong>Discussion and implications: </strong>This study showed that to optimize implementation of AI-driven lifestyle monitoring, organizations should address privacy concerns, provide training, engage in system (re)design and create a shared vision. A comprehensive multi-level approach across all levels is essential for successful AI integration in long-term care for older adults.</p>","PeriodicalId":51347,"journal":{"name":"Gerontologist","volume":" ","pages":""},"PeriodicalIF":3.2000,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Gerontologist","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/geront/gnaf230","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GERONTOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Background and objectives: AI-driven lifestyle monitoring systems collect data from ambient, motion, contact, light, and physiological sensors placed in the home, enabling AI algorithms to identify daily routines and detect deviations to support older adults "aging in place." Despite its potential to support several challenges in long-term care for older adults, implementation remains limited. This study explored the facilitators and barriers to implementing AI-driven lifestyle monitoring in long-term care for older adults, as perceived by formal and informal caregivers, as well as management, in both an adopting and non-adopting healthcare organization.
Research design and methods: A qualitative interview study using semi-structured interviews was conducted with 22 participants (5 informal caregivers, 10 formal caregivers, and 7 participants in a management position) from two long-term care organizations. Reflexive thematic analysis, guided by the nonadoption, abandonment, scale-up, spread, and sustainability (NASSS) framework, structured findings into facilitators and barriers.
Results: 12 facilitators and 16 barriers were identified, highlighting AI-driven lifestyle monitoring as a valuable, patient-centred, and unobtrusive tool enhancing care efficiency and caregiver reassurance. However, barriers such as privacy concerns, notification overload, training needs, and organizational alignment must be addressed. Contextual factors, including regulations, partnerships, and financial considerations, further influence implementation.
Discussion and implications: This study showed that to optimize implementation of AI-driven lifestyle monitoring, organizations should address privacy concerns, provide training, engage in system (re)design and create a shared vision. A comprehensive multi-level approach across all levels is essential for successful AI integration in long-term care for older adults.
期刊介绍：
The Gerontologist, published since 1961, is a bimonthly journal of The Gerontological Society of America that provides a multidisciplinary perspective on human aging by publishing research and analysis on applied social issues. It informs the broad community of disciplines and professions involved in understanding the aging process and providing care to older people. Articles should include a conceptual framework and testable hypotheses. Implications for policy or practice should be highlighted. The Gerontologist publishes quantitative and qualitative research and encourages manuscript submissions of various types including: research articles, intervention research, review articles, measurement articles, forums, and brief reports. Book and media reviews, International Spotlights, and award-winning lectures are commissioned by the editors.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
