METHODS: The MEDLINE, EMBASE, CINAHL, and Web of Science databases until October 2022 without any language restriction were systematically searched to identify preoperative independent variables related to 30-day mortality following PCI. Information was systematically summarised in a descriptive manner following the Checklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies checklist. The quality and risk of bias of all included articles were assessed using the Prediction Model Risk Of Bias Assessment Tool. Two independent investigators took part in screening and quality assessment.
RESULTS: The search yielded 2,941 studies, of which 42 articles were included in the final assessment. Logistic regression, Cox-proportional hazard model, and machine learning were utilised by 27 (64.3%), 14 (33.3%), and one (2.4%) article, respectively. A total of 74 independent preoperative variables were identified that were significantly associated with 30-day mortality following PCI. Variables that repeatedly used in various models were, but not limited to, age (n=36, 85.7%), renal disease (n=29, 69.0%), diabetes mellitus (n=17, 40.5%), cardiogenic shock (n=14, 33.3%), gender (n=14, 33.3%), ejection fraction (n=13, 30.9%), acute coronary syndrome (n=12, 28.6%), and heart failure (n=10, 23.8%). Nine (9; 21.4%) studies used missing values imputation, and 15 (35.7%) articles reported the model\'s performance (discrimination) with values ranging from 0.501 (95% confidence interval [CI] 0.472-0.530) to 0.928 (95% CI 0.900-0.956), and four studies (9.5%) validated the model on external/out-of-sample data.
CONCLUSIONS: Risk adjustment models need further improvement in their quality through the inclusion of a parsimonious set of clinically relevant variables, appropriately handling missing values and model validation, and utilising machine learning methods.
方法:MEDLINE,EMBASE,CINAHL,我们对2022年10月之前没有任何语言限制的WebofScience数据库进行了系统搜索,以确定与PCI术后30日死亡率相关的术前独立变量.在关键评估清单和数据提取清单之后,以描述性方式系统地总结了信息,以系统地审查预测建模研究清单。使用预测模型偏差风险评估工具评估所有纳入文章的质量和偏差风险。两名独立的研究者参与了筛查和质量评估。
结果:搜索产生了2,941项研究,其中42篇文章被纳入最终评估。Logistic回归,Cox比例风险模型,27人(64.3%)使用了机器学习,14(33.3%),和一篇(2.4%)文章,分别。共有74个独立的术前变量与PCI术后30天死亡率显著相关。在各种模型中重复使用的变量是,但不限于,年龄(n=36,85.7%),肾脏疾病(n=29,69.0%),糖尿病(n=17,40.5%),心源性休克(n=14,33.3%),性别(n=14,33.3%),射血分数(n=13,30.9%),急性冠脉综合征(n=12,28.6%),和心力衰竭(n=10,23.8%)。九项(9;21.4%)研究使用缺失值插补,15篇(35.7%)文章报告了模型的性能(辨别),值范围从0.501(95%置信区间[CI]0.472-0.530)到0.928(95%CI0.900-0.956),四项研究(9.5%)在外部/样本外数据上验证了该模型。
结论:风险调整模型需要通过纳入一组简约的临床相关变量来进一步提高其质量,正确处理缺失值和模型验证,并利用机器学习方法。