时间标签：数据日期 2026-11-05 · 生成时间 2026-11-05 05:30（Asia/Shanghai）｜ 检索窗口 PubMed edat 2026/11/02 – 2026/11/06 ｜ 情报发生日期 2026-11-05
研究问题
Such approaches have difficulty effectively addressing the personalized and dynamic evolution of user needs and fail to achieve a refined balance among multiple objectives including safety, comfort, energy efficiency, and cost.In recent years, the rapid development of advanced digital technologies such as artificial intelligence (AI), the Internet of Things (IoT), and big data has provided new approaches to addressing these challenges.；With the introduction of AI technologies, site selection methods are shifting from static resource allocation toward intelligent decision-support systems that can simulate dynamic supply and demand and balance multiple objectives.；This helps reveal the complex mechanisms of multi-factor coupling and enhances the transparency and credibility of model decisions.3.1.2Site selection decision-making under multi-objective coordinationTraditional multi-objective optimization methods for site selection such as weighted-sum and ε-constraint methods often rely on prior knowledge to determine weights, thereby transforming multi-objective problems into single-objective ones (41).
方法
Established building lifecycle theory typically describes the lifecycle as a sequence of stages including initiation, project definition, design, construction, commissioning, operation, maintenance, refurbishment, replacement, deconstruction and so on (26).；Regarding specific methodologies, these studies commonly use questionnaires, census data, or health databases to obtain information on older adults’ socioeconomic attributes, health status, and disability levels, and then apply clustering algorithms (e.g., K-means and spectral clustering) to identify groups of older adults with similar needs and map their spatial distributions.；Conventional post-occupancy evaluation (POE) mainly relies on periodic questionnaires and interviews, which are often delayed, subjective, and unable to capture dynamic behaviors.
核心结论
The operational data collected in these settings also provide empirical evidence for understanding spatial use patterns and supporting optimized design.Collectively, these studies indicate that AI technologies are gradually being embedded in environmental perception, data analysis, intelligent decision-making, and system optimization, thereby driving older adult care and the built environment toward smarter and more dynamically adaptive directions, while creating new opportunities to improve care quality.；AI-related intelligent computational techniques were included only when their specific applications demonstrated such capabilities.；ML models such as decision tree (DT) and random forest (RF) models demonstrate distinctive advantages in processing POI data and mining spatial association patterns (34, 35).
局限
The environmental quality of LTCFs directly affects residents’ safety, health, and overall quality of life (3, 4).However, current practices for LTCFs face multiple challenges.；However, reviews that examine AI-enabled spatial optimization of LTCF environments remain scarce (19).；However, these methods struggle to capture dynamic changes in demographic structures or varying care needs.
对本项目的价值
中等价值：属「生物标志物 / 建模方法学」方向；方法学 / 生物标志物 / AI 建模栏目可用作本项目文献库与综述素材。 ｜ 价值分 2.9/5（★★★☆☆）
全文来源
PubMed PMC JATS（正文 59,835 字符，题名指纹 1.0，已过 PubMed PMCID 官方关联 + 题名指纹 + 正文长度归属校验）
原文题录
- 中文题名：人工智能在长期照护机构的应用：规划、设计、运营与评估的范围综述
- 英文标题：Artificial intelligence applications in long-term care facilities: a scoping review across planning, design, operation, and assessment.
- 期刊与标识：Frontiers in public health · PMID 42973547 · DOI 10.3389/fpubh.2026.1974526 · PMC PMC13724337