目的 系统性评价ICU经口气管插管患者口腔黏膜压力性损伤风险的预测模型，为临床医护人员挑选或设计出适宜的评估工具提供依据。方法 系统检索PubMed、Embase、Web of Science、Cochrane Library、CINAHL、中国知网、维普数据库、万方数据库和中国生物医学文献数据库自建库至2025年2月1日发表的关于构建ICU经口气管插管患者口腔黏膜压力性损伤风险预测模型的研究。由两名研究者独立进行文献筛选、数据提取，并运用预测模型偏倚风险评估工具评估纳入文献的偏倚风险。结果 共纳入10项研究，涉及10个模型。气管插管留置时间、白蛋白、急性生理学和慢性健康状况Ⅱ（Acute Physiology and Chronic Health EvaluationⅡ，APACHE Ⅱ）评分、Richmond躁动-镇静评分量表（Richmond Agitation-Sedation Scale，RASS）评分和牙垫的使用是模型重复报告的前5名预测变量。8项研究报告了受试者操作特征曲线下面积为0.600~0.930。10项研究适用性良好但普遍存在高偏倚风险，尤以数据分析领域突出。结论 ICU经口气管插管患者口腔黏膜压力性损伤风险预测模型研究仍处于初期阶段。未来需开展高质量研究，结合人工智能优化模型开发与临床转化，重点加强模型内外部验证，并关注气管插管留置时间、APACHE Ⅱ评分及牙垫使用等核心预测因子。

Objective To systematically review prediction models for the risk of oral mucosa pressure injury in ICU patients with orotracheal intubation，aiming to assist clinical healthcare professionals in selecting or designing appropriate assessment tools. Methods We systematically searched PubMed，Embase，Web of Science，Cochrane Library，CINAHL，China National Knowledge Infrastructure，VIP Database，Wanfang Database，and China Biological Medicine Literature Database for studies published from database inception to February 1，2025，focusing on the development of risk prediction models for oral mucosa pressure injuries in ICU patients with orotracheal intubation. Two researchers independently performed literature screening and data extraction. The Prediction model Risk of Bias Assessment Tool（PROBAST） was applied to assess the risk of bias in the included studies. Results Ten studies involving 10 distinct prediction models were included. The top five most frequently reported predictor variables were duration of intubation，albumin level，acute physiology and chronic health evaluationⅡ（APACHEⅡ），Richmond Agitation-Sedation Scale score（RASS），and bite block usage. Eight studies reported area under the receiver operating characteristic curve（AUC） values ranging from 0.600 to 0.930. While the applicability of all ten studies was rated as good，they universally exhibited a high risk of bias，particularly in the domain of analysis. Conclusion Research on prediction models for oral mucosa pressure injury risk in ICU patients with orotracheal intubation remains in its early stages. Future studies should focus on conducting high-quality research，incorporating artificial intelligence to optimize model development and clinical translation. Emphasis should be placed on strengthening both internal and external validation of models，with particular attention to core predictors such as duration of intubation，APACHE Ⅱ score，and bite block usage.