危重症患者肠内喂养不耐受风险预测模型的系统评价

Risk prediction models for enteral feeding intolerance in critically ill patients:a systematic review

目的 系统评价危重症患者肠内喂养不耐受(enteral feeding intolerance,EFI)风险预测模型,为后期模型开发提供依据。方法 系统检索中国知网、万方数据库、维普期刊库、中国生物医学文献数据库、PubMed、Embase、Web of Science、Cochrane Library、CINAHL中截至2023年11月19日发表的危重症患者EFI风险预测模型相关文献,语种限定为中文和英文。2名研究者独立筛选文献、提取数据,并使用PROBAST工具评估纳入研究的偏倚风险和适用性。结果 共纳入19篇文献,包含24个预测模型,受试者操作特征曲线下面积为0.700~0.940。重复报告现频次最高的预测因子为急性生理与慢性健康状况Ⅱ评分、腹内压和白蛋白水平。纳入研究的总体适用性较好,但总体偏倚风险较高,主要体现在基于回顾性数据来源、结局定义包含预测因子、样本量偏小、连续性变量和缺失数据处理不当、单因素分析法筛选因子和模型性能评估不全。结论 现有的危重症患者EFI风险预测模型研究尚处在发展阶段,模型开发和验证中存在部分方法学缺陷,未来需要引入更敏感和可重复的胃肠道功能障碍评价指标,并根据个体预后或诊断多变量预测模型透明报告规范报告研究结果。

Objective To systematically evaluate the prediction models of enteral feeding intolerance(EFI)in critically ill patients to provide references for subsequent model development.Methods Relative articles on the prediction models of EFI in critically ill patients were retrieved from CNKI,Wanfang,VIP,CBM,PubMed,Embase,Web of Science,Cochrane Library and CINAHL from the establishment of the databases to November 19,2023.Language limited to Chinese and English.Two researchers independently screened,extracted data,and assessed bias risk and applicability by PROBAST.Results 19 studies were included,involving 24 models with an area under the subject working characteristic curve of 0.700~0.940.The independent predictors repeatedly reported were APACHE I score,intra-abdominal pressure and serum albumin levels.19 studies had good applicability but high risks of bias due to existing data sources,outcome definitions incorporating the predictors,small sample size,inappropriate handling of continuous variables and missing data,incomplete univariate analysis for predictors selection,and incomplete model performance assessment.Conclusion Existing predictive models for EFI in critically ill patients are still in the initial stage,as they have methodological defects.Future research should incorporate more sensitive and reproducible indicators for evaluating gastrointestinal dysfunction and fllow the TRIPOD guidelines for reporting the results.