目的 采用Meta分析评价机器学习在术中出血量评估中的应用价值，为相关模型的开发与临床应用提供参考。方法 检索中国知网、万方、PubMed等国内外数据库中有关基于机器学习评估术中出血量的中英文文献，检索时间为建库至2025年11月。采用Stata 17.0软件对纳入文献进行Meta分析。结果 共纳入12篇研究，整合后机器学习模型评估出血量的结果与金标准具有强相关性[r=0.91,95%CI(0.84~0.95)]。亚组分析结果显示，发表年份、国家、研究对象、样本类型、机器学习模型、是否外部检验的差异存在统计学意义（均P＜0.001）。结论 机器学习模型在术中出血量评估中准确性和可靠性高，其应用有助于护士精准高效评估出血量，为抢救生命争取时间，对降低围术期严重并发症发生率、保障患者安全意义重大。

Objective To evaluate the application value of machine learning in the assessment of intraoperative blood loss using Meta-analysis,and to provide a reference for the development and clinical application of related models.Methods Chinese and English literatures on machine learning-based assessment of intraoperative blood loss were retrieved from databases such as CNKI,Wanfang,and PubMed from the inception to November 2025.Stata 17.0 software was used for the Meta-analysis.Results A total of 12 studies were included.After integration,there was a strong correlation between the machine learning model and the gold standard in the assessment of intraoperative blood loss [r=0.91,95%CI (0.84-0.95)].Subgroup analysis showed that there were statistically significant differences in publication year,country,research object,sample type,machine learning model,and whether external validation was performed (all P＜0.001).Conclusions Machine learning models have high accuracy and reliability in the assessment of intraoperative blood loss.Its application can help nurses evaluate blood loss accurately and efficiently,and gain time for life-saving rescue.It is of great significance for reducing the incidence of severe perioperative complications and ensuring patient safety.

R473.6

上海交通大学“交大之星”计划医工交叉研究基金（YG2024ZD26）