时间标签：数据日期 2026-11-01 · 生成时间 2026-11-01 05:30（Asia/Shanghai）｜ 检索窗口 PubMed edat 2026/10/31–2026/11/01 ｜ 情报发生日期 2026-11-01
研究问题
Moreover, traditional risk prediction models mainly rely on linear approaches such as logistic regression, which are often incapable of capturing complex nonlinear interactions among variables, thus limiting their predictive accuracy ( ).；In recent years, machine learning, a key branch of artificial intelligence, has been increasingly applied in the field of medical risk assessment and prediction.
方法
By calculating SHAP values to quantify the contribution of each variable, it helps to understand how each variable influences the model output ( ). 2.9 Statistical analysis Statistical analysis was performed using IBM SPSS Statistics 25.0…；For continuous variables, those with less than 5% missing data were imputed using the mean (for normally distributed variables) or the median (for skewed variables).；Categorical variables were expressed as frequencies (percentages), and comparisons between groups were performed using the chi-square test or Fisher's exact test.
核心结论
Reduced cognitive and brain reserve may diminish the ability of older patients to maintain cerebral function in the face of transient disturbances in perfusion, metabolism, neurotransmission, and arousal.；Importantly, however, this interpretation does not imply that EA and POD are equivalent, nor does it establish reduced cerebral reserve, neuroinflammation, or altered stress responses as causal mechanisms of EA.；Thus, cognitive impairment and anxiety may be clinically relevant not only as individual predictors, but also as markers of reduced resilience to subsequent perioperative stress.；Taken together, the pattern of predictors identified in this study is consistent with a vulnerability–stressor framework of acute perioperative brain dysfunction.
局限
Future studies should include larger, multicenter cohorts covering a broader range of geriatric orthopedic surgical settings and should perform independent external validation to assess model transportability.；Nevertheless, direct comparisons across studies should be interpreted cautiously because of differences in study populations, predictor sets, outcome definitions, and validation strategies.
对本项目的价值
人群纵向证据，可用于假说生成与终点选择：方法学可复用：建模流程与验证策略可直接迁移到衰老时钟 / 终点研究。 ｜ 价值分 1.0/5（★☆☆☆☆）
全文来源
PubMed PMC JATS 全文（正文 38,415 字符，已过 DOI 逐字 + 题名指纹双重归属校验）
原文题录
- 英文标题：Development and validation of a machine learning-based prediction model for emergence agitation in geriatric patients undergoing orthopedic surgery: a prospective cohort study.
- 期刊与标识：Frontiers in medicine · PMID 42953249 · DOI 10.3389/fmed.2026.1903005
A 级证据分级：A 级（同行评议人体研究）
本文属人体研究证据，但需注意：观察性或小样本干预的结论不等于已证实临床获益；效应量与长期安全性仍需更大规模、更长随访的试验验证。
关于本文的文献来源：本站依据 IMA 知识库「五刊监控·深度文献卡片」撰写，依据已获取的期刊全文（方法、样本量与结论已回到原文核对）；未能获取全文的同批条目另行标注「摘要级」，全程未做任何数值推算补全。