Key points are not available for this paper at this time.
Background/Objectives: The global aging population has placed escalating demands on long-term care systems, with nursing homes facing persistent challenges including chronic understaffing, high staff turnover, complex resident acuity, and elevated risk of adverse events. Artificial intelligence (AI)—encompassing machine learning, natural language processing, and computer vision—presents a transformative opportunity to address these systemic pressures by enabling proactive, data-driven care delivery. This rapid review aims to systematically map the existing literature on AI applications in nursing facilities, categorize how these technologies contribute to improvements in quality of care, and identify gaps warranting further investigation. Methods: Following Arksey and O’Malley’s framework and PRISMA-ScR guidelines, we conducted a comprehensive search of academic literature using a predefined Boolean string. The extracted data were organized and analyzed thematically. Results: The synthesized literature (n = 28 studies) revealed seven primary themes: (1) Clinical management, risk prediction, and monitoring; (2) Pressure injuries, wound management, and diagnostics; (3) Objective assessment, mental health, and end-of-life care; (4) Nutrition and personalized daily support; (5) Operational efficiency and staffing; (6) Technical, infrastructure, and economic barriers; and (7) Social, ethical, and demographic considerations. Conclusions: AI holds considerable promise for enhancing the quality of care in nursing homes across clinical, operational, and social domains. However, widespread adoption remains constrained by prohibitive infrastructure costs, data privacy regulations, algorithmic bias, staff resistance, and limited generalizability of findings across diverse populations. Successful integration requires evidence-based implementation frameworks and standardized and interoperable platforms.
Mileski et al. (Mon,) studied this question.