Artificial intelligence applications in long-term care facilities: a scoping review across planning, design, operation, and assessment
- 1Institute of Architectural Design and Theoretical Research, College of Civil Engineering and Architecture, Zhejiang University
- 2College of Architecture and Urban Planning, Beijing University of Technology
Abstract
Introduction: Improving the quality of long-term care facilities (LTCFs) is critical to safeguarding the health, safety, dignity, and quality of life of older adults amid global population aging. However, traditional design methods for LTCFs rely heavily on static codes and empirical judgment, limiting their ability to respond to dynamic care needs and balance multiple objectives across lifecycle stages. To address these limitations, artificial intelligence (AI) offers a promising solution through dynamic optimization and intelligent decision-making.
Methods: A scoping review was conducted to systematically map the applications of AI in LTCFs across four lifecycle stages: planning and site selection, architectural design, operation and management, and assessment and retrofit. Searches were performed in Web of Science, Scopus, Google Scholar, SAGE Journals, and CNKI for literature published between January 2010 and December 2025, resulting in the inclusion of 38 eligible publications. The review was guided by the methodological framework proposed by Arksey and O’Malley and reported in accordance with PRISMA-ScR.
Results: Four main application pathways were identified, including prediction and evaluation, generation and evolution, sensing and recognition, and simulation and modeling. Specifically, AI was applied to site-selection evaluation and demand forecasting during planning; spatial layout generation and intelligent equipment integration during design; safety monitoring, behavior recognition, and environmental control during operation; and comfort and safety assessment and retrofit optimization during assessment. Research was concentrated in operation and management, whereas evidence on assessment and retrofit remained limited.
Discussion: Overall, AI shows potential to shift LTCFs from static, fragmented, and experience-based practices toward more data-informed, adaptive, and person-centered care environments. However, implementation remains constrained by data quality and standardization, facility heterogeneity, system integration, equitable access, privacy, and ethical concerns. This review provides planners, architects, engineers, care providers, facility managers, and public health decision-makers with a technology roadmap and identifies priorities for using AI-enabled built environments to support high-quality older adult care and sustainable long-term care systems.
Related
- Clinical Translation of Artificial Intelligence in Oncology: Real-World Validation, Workflow Integration, and Precision Medicine Applications
- Artificial intelligence-enabled mental health applications for adolescents: a scoping review of safety, effectiveness and clinical implementation
- Artificial Intelligence Applications in Laser-Assisted Refractive Surgery—A Comprehensive Review
- From underdiagnosis to scalable screening: Applications of artificial intelligence for vertebral compression fracture detection – a systematic review and meta-analysis of diagnostic performance
- Artificial Intelligence in Gingival Recession Assessment and Treatment Planning: A Scoping Review
BibTeX
@article{chen2026artificial,
title = {{Artificial intelligence applications in long-term care facilities: a scoping review across planning, design, operation, and assessment}},
author = {Yu Chen and Xinlan Song and Ning Sun and Jianan Li and Zhi Qiu},
journal = {Frontiers in Public Health},
year = {2026},
month = oct,
doi = {10.3389/fpubh.2026.1974526},
url = {https://www.frontiersin.org/articles/10.3389/fpubh.2026.1974526/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Artificial intelligence applications in long-term care facilities: a scoping review across planning, design, operation, and assessment
AU - Yu Chen
AU - Xinlan Song
AU - Ning Sun
AU - Jianan Li
AU - Zhi Qiu
PY - 2026
DA - 2026/10/19
JO - Frontiers in Public Health
DO - 10.3389/fpubh.2026.1974526
UR - https://www.frontiersin.org/articles/10.3389/fpubh.2026.1974526/full
AB - Introduction: Improving the quality of long-term care facilities (LTCFs) is critical to safeguarding the health, safety, dignity, and quality of life of older adults amid global population aging. However, traditional design methods for LTCFs rely heavily on static codes and empirical judgment, limiting their ability to respond to dynamic care needs and balance multiple objectives across lifecycle stages. To address these limitations, artificial intelligence (AI) offers a promising solution through dynamic optimization and intelligent decision-making. Methods: A scoping review was conducted to systematically map the applications of AI in LTCFs across four lifecycle stages: planning and site selection, architectural design, operation and management, and assessment and retrofit. Searches were performed in Web of Science, Scopus, Google Scholar, SAGE Journals, and CNKI for literature published between January 2010 and December 2025, resulting in the inclusion of 38 eligible publications. The review was guided by the methodological framework proposed by Arksey and O’Malley and reported in accordance with PRISMA-ScR. Results: Four main application pathways were identified, including prediction and evaluation, generation and evolution, sensing and recognition, and simulation and modeling. Specifically, AI was applied to site-selection evaluation and demand forecasting during planning; spatial layout generation and intelligent equipment integration during design; safety monitoring, behavior recognition, and environmental control during operation; and comfort and safety assessment and retrofit optimization during assessment. Research was concentrated in operation and management, whereas evidence on assessment and retrofit remained limited. Discussion: Overall, AI shows potential to shift LTCFs from static, fragmented, and experience-based practices toward more data-informed, adaptive, and person-centered care environments. However, implementation remains constrained by data quality and standardization, facility heterogeneity, system integration, equitable access, privacy, and ethical concerns. This review provides planners, architects, engineers, care providers, facility managers, and public health decision-makers with a technology roadmap and identifies priorities for using AI-enabled built environments to support high-quality older adult care and sustainable long-term care systems.
SN - 2296-2565
ER -