Table_3_Machine learning in predicting cardiac surgery-associated acute kidney injury: A systemic review and meta-analysis.DOCX

BackgroundCardiac surgery-associated acute kidney injury (CSA-AKI) is a common complication following cardiac surgery. Early prediction of CSA-AKI is of great significance for improving patients' prognoses. The aim of this study is to systematically evaluate the predictive performance of machine learning models for CSA-AKI.
MethodsCochrane Library, PubMed, EMBASE, and Web of Science were searched from inception to 18 March 2022. Risk of bias assessment was performed using PROBAST. Rsoftware (version 4.1.1) was used to calculate the accuracy and C-index of CSA-AKI prediction. The importance of CSA-AKI prediction was defined according to the frequency of related factors in the models.
ResultsThere were 38 eligible studies included, with a total of 255,943 patients and 60 machine learning models. The models mainly included Logistic Regression (n = 34), Neural Net (n = 6), Support Vector Machine (n = 4), Random Forest (n = 6), Extreme Gradient Boosting (n = 3), Decision Tree (n = 3), Gradient Boosted Machine (n = 1), COX regression (n = 1), κNeural Net (n = 1), and Naïve Bayes (n = 1), of which 51 models with intact recording in the training set and 17 in the validating set. Variables with the highest predicting frequency included Logistic Regression, Neural Net, Support Vector Machine, and Random Forest. The C-index and accuracy wer 0.76 (0.740, 0.780) and 0.72 (0.70, 0.73), respectively, in the training set, and 0.79 (0.75, 0.83) and 0.73 (0.71, 0.74), respectively, in the test set.
ConclusionThe machine learning-based model is effective for the early prediction of CSA-AKI. More machine learning methods based on noninvasive or minimally invasive predictive indicators are needed to improve the predictive performance and make accurate predictions of CSA-AKI. Logistic regression remains currently the most commonly applied model in CSA-AKI prediction, although it is not the one with the best performance. There are other models that would be more effective, such as NNET and XGBoost.
Systematic review registrationhttps://www.crd.york.ac.uk/; review registration ID: CRD42022345259.

背景 心脏手术相关急性肾损伤（Cardiac surgery-associated acute kidney injury, CSA-AKI）是心脏手术后常见的并发症。早期预测CSA-AKI对改善患者预后具有重要临床意义。本研究旨在系统评价机器学习模型用于CSA-AKI预测的效能。
方法 本研究检索了Cochrane图书馆、PubMed、EMBASE及Web of Science数据库，检索时限为各数据库建库至2022年3月18日。采用PROBAST工具进行偏倚风险评估。使用R软件（版本4.1.1）计算CSA-AKI预测模型的准确率与C指数。根据相关因素在模型中的出现频率，定义CSA-AKI预测因子的重要性。
结果 最终纳入38项符合标准的研究，共纳入255944例患者，涉及60个机器学习预测模型。所纳入的模型主要包括：Logistic回归（Logistic Regression，n=34）、神经网络（Neural Net，n=6）、支持向量机（Support Vector Machine，n=4）、随机森林（Random Forest，n=6）、极端梯度提升（Extreme Gradient Boosting，n=3）、决策树（Decision Tree，n=3）、梯度提升机（Gradient Boosted Machine，n=1）、COX回归（COX regression，n=1）、κ神经网络（κNeural Net，n=1）及朴素贝叶斯（Naïve Bayes，n=1）；其中训练集记录完整的模型共51个，验证集模型共17个。出现频率最高的预测相关变量依次为Logistic回归、神经网络、支持向量机及随机森林。训练集的C指数与准确率分别为0.76（95%置信区间：0.740, 0.780）与0.72（95%置信区间：0.70, 0.73）；测试集的C指数与准确率分别为0.79（95%置信区间：0.75, 0.83）与0.73（95%置信区间：0.71, 0.74）。
结论 基于机器学习的预测模型可有效实现CSA-AKI的早期预测。未来仍需开发更多基于无创或微创预测指标的机器学习方法，以提升CSA-AKI的预测效能并实现精准预测。目前Logistic回归仍是CSA-AKI预测中应用最广泛的模型，尽管其并非性能最优的模型；另有部分模型（如神经网络与极端梯度提升）的预测效能更为优异。
系统评价注册 本系统评价已注册，注册链接：https://www.crd.york.ac.uk/；注册编号：CRD42022345259。