Artificial intelligence in geriatric healthcare: a scoping review

Le résumé fourni par la source

BACKGROUND: Deep demographic ageing is triggering a twin crisis in healthcare: a rising prevalence of multimorbidity among older adults and a severe global shortage of healthcare professionals, particularly nursing staff, which together create life-threatening gaps in long-term care. Although artificial intelligence shows significant potential to alleviate these pressures by improving the efficiency and accessibility of geriatric healthcare, its integration faces critical challenges spanning systemic, user-level, and societal dimensions. OBJECTIVE: This review aims to systematically analyze the current applications of artificial intelligence in geriatric healthcare, identify key barriers hindering its effective integration, and propose stakeholder-specific roadmaps. METHODS: This scoping review follows the PRISMA-ScR guidelines. This review was conducted using a two-step search strategy from five databases: PubMed, MEDLINE, the Cochrane Library, EMBASE, and Web of Science. First, a comprehensive search was performed across five electronic databases for literature published between January 1, 2015, and September 30, 2025. Second, the reference lists of identified studies and relevant reviews were manually screened. The study selection followed the PCC framework, focusing on evidence of artificial intelligence applications, implementation challenges, and proposed solutions in geriatric healthcare. RESULTS: Artificial intelligence is extensively applied across five key domains in geriatrics: health monitoring and disease management, safety supervision and risk prevention, cognitive and mental health support, social interaction and emotional companionship, and daily living assistance. Despite this potential, three major barrier categories were identified: (1) Systemic fractures; (2) User-level resistance, and (3) A widening social divide. In response, the study proposes concrete roadmaps, such as mandating Fast Healthcare Interoperability Resources standards for data interoperability, establishing ethical artificial intelligence certification, deploying culturally adaptive designs, and initiating workforce upskilling programs. CONCLUSIONS: Artificial intelligence holds significant promise for mitigating the global geriatric healthcare crisis exacerbated by demographic aging and nursing shortages. However, realizing its full potential requires a coordinated, multi-stakeholder approach to overcome the entrenched systemic, human, and social obstacles. The proposed roadmaps provide an actionable framework that may facilitate the development of artificial intelligence systems that are more efficient, equitable, and human-centered, pending empirical validation in real-world settings. REGISTRATION: The protocol has been registered on OSF.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.