Disability and rehabilitation. Assistive technology · 2026
Mobility wearable devices in older adults: a scoping review of hardware, artificial intelligence software and socio-ecological influences on device use.
СтатьяОбзорНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Suri Harjot, Hillman Areeya, Chan Ashely, Onyekere Chukwuebuka P, Kumapayi Peace, Chan Ethan, Mehta Ambika, Kalu Michael E
Аннотация
PURPOSE: This scoping review maps mobility wearable device hardware and artificial intelligence(AI) software and synthesise socioecological factors influencing device use among older adults aged 65 years and older.
METHODS: We followed the Arksey and O'Malley five-step framework and searched five databases and one data interface (OVID) between January 2010 to December 2025. Two reviewers independently screened studies and extracted data in Covidence© using predefined eligibility criteria. Data were analysed in pairs and synthesised using the socio-ecological framework and an AI taxonomy (unsupervised, semi-supervised, supervised, deep learning and reinforcement learning).
RESULTS: We included 197 studies from 27 countries, predominantly quantitative (97.0%). Mobility monitoring relied on accelerometers (63.5%), plastic (87%) and worn at the hip/waist. Fourteen studies employed AI-enabled analytics, of which 13 used supervised learning and one used both supervised and deep learning approaches. A socioecological framework guided us to derived 22 themes, 10 opportunities and 12 challenges, across individual, interpersonal, environmental and policy levels. Real-time mobility monitoring with feedback was the unifying opportunity, while privacy, data governance, trust and digital literacy inequities were recurring constraints, underscoring the need for inclusive, equity-oriented design. Level-specific opportunities included cognitive and mental health benefits (individual), social motivation (interpersonal), workforce efficiency (organisational) and reimbursement evolution (policy). Level-specific challenges included acceptability (individual), autonomy and dependence tensions (interpersonal), standardisation and integration barriers (organisational) and regulatory gaps (policy).
CONCLUSION: The evidence base remains methodologically fragmented, with limited longitudinal real-world evaluation of AI models. Progress will require addressing multilevel implementation, integration and equity barriers that shape real world adoption among older adults.
METHODS: We followed the Arksey and O'Malley five-step framework and searched five databases and one data interface (OVID) between January 2010 to December 2025. Two reviewers independently screened studies and extracted data in Covidence© using predefined eligibility criteria. Data were analysed in pairs and synthesised using the socio-ecological framework and an AI taxonomy (unsupervised, semi-supervised, supervised, deep learning and reinforcement learning).
RESULTS: We included 197 studies from 27 countries, predominantly quantitative (97.0%). Mobility monitoring relied on accelerometers (63.5%), plastic (87%) and worn at the hip/waist. Fourteen studies employed AI-enabled analytics, of which 13 used supervised learning and one used both supervised and deep learning approaches. A socioecological framework guided us to derived 22 themes, 10 opportunities and 12 challenges, across individual, interpersonal, environmental and policy levels. Real-time mobility monitoring with feedback was the unifying opportunity, while privacy, data governance, trust and digital literacy inequities were recurring constraints, underscoring the need for inclusive, equity-oriented design. Level-specific opportunities included cognitive and mental health benefits (individual), social motivation (interpersonal), workforce efficiency (organisational) and reimbursement evolution (policy). Level-specific challenges included acceptability (individual), autonomy and dependence tensions (interpersonal), standardisation and integration barriers (organisational) and regulatory gaps (policy).
CONCLUSION: The evidence base remains methodologically fragmented, with limited longitudinal real-world evaluation of AI models. Progress will require addressing multilevel implementation, integration and equity barriers that shape real world adoption among older adults.