Department of Big Data Center for Cardiovascular Disease, Heart Center of Henan Provincial People's Hospital, Fuwai Central China Cardiovascular Hospital, Central China Fuwai Hospital of Zhengzhou University, Zhengzhou, China.
Department of Cardiovascular Surgery, Heart Center of Henan Provincial People's Hospital, Fuwai Central China Cardiovascular Hospital, Central China Fuwai Hospital of Zhengzhou University, Zhengzhou, China.
BMC Nephrol. 2023 Nov 7;24(1):326. doi: 10.1186/s12882-023-03324-w.
OBJECTIVE: Postoperative acute kidney injury (PO-AKI) is a common complication after cardiac surgery. We aimed to evaluate whether machine learning algorithms could significantly improve the risk prediction of PO-AKI. METHODS: The retrospective cohort study included 2310 adult patients undergoing cardiac surgery in a tertiary teaching hospital, China. Postoperative AKI and severe AKI were identified by the modified KDIGO definition. The sample was randomly divided into a derivation set and a validation set based on a ratio of 4:1. Exploiting conventional logistic regression (LR) and five ML algorithms including decision tree, random forest, gradient boosting classifier (GBC), Gaussian Naive Bayes and multilayer perceptron, we developed and validated the prediction models of PO-AKI. We implemented the interpretation of models using SHapley Additive exPlanation (SHAP) analysis. RESULTS: Postoperative AKI and severe AKI occurred in 1020 (44.2%) and 286 (12.4%) patients, respectively. Compared with the five ML models, LR model for PO-AKI exhibited the largest AUC (0.812, 95%CI: 0.756, 0.860, all P < 0.05), sensitivity (0.774, 95%CI: 0.719, 0.813), accuracy (0.753, 95%CI: 0.719, 0.781) and Youden index (0.513, 95%CI: 0.451, 0.573). Regarding severe AKI, GBC algorithm showed a significantly higher AUC than the other four ML models (all P < 0.05). Although no significant difference (P = 0.173) was observed in AUCs between GBC (0.86, 95%CI: 0.808, 0.902) and conventional logistic regression (0.803, 95%CI: 0.746, 0.852), GBC achieved greater sensitivity, accuracy and Youden index than conventional LR. Notably, SHAP analyses showed that preoperative serum creatinine, hyperlipidemia, lipid-lowering agents and assisted ventilation time were consistently among the top five important predictors for both postoperative AKI and severe AKI. CONCLUSION: Logistic regression and GBC algorithm demonstrated moderate to good discrimination and superior performance in predicting PO-AKI and severe AKI, respectively. Interpretation of the models identified the key contributors to the predictions, which could potentially inform clinical interventions.
目的：术后急性肾损伤（PO-AKI）是心脏手术后的常见并发症。本研究旨在评估机器学习算法是否能显著提高 PO-AKI 的风险预测能力。
方法：本回顾性队列研究纳入了在中国一家三级教学医院接受心脏手术的 2310 例成年患者。根据改良 KDIGO 定义，术后 AKI 和重度 AKI 由术后 AKI 和重度 AKI 定义。根据 4:1 的比例，将样本随机分为推导集和验证集。利用传统逻辑回归（LR）和包括决策树、随机森林、梯度提升分类器（GBC）、高斯朴素贝叶斯和多层感知器在内的 5 种 ML 算法，我们开发并验证了 PO-AKI 的预测模型。我们使用 SHapley Additive exPlanation（SHAP）分析对模型进行解释。
结果：术后 AKI 和重度 AKI 分别发生在 1020 例（44.2%）和 286 例（12.4%）患者中。与 5 种 ML 模型相比，LR 模型对 PO-AKI 的 AUC（0.812，95%CI：0.756，0.860，均 P<0.05）、敏感性（0.774，95%CI：0.719，0.813）、准确性（0.753，95%CI：0.719，0.781）和 Youden 指数（0.513，95%CI：0.451，0.573）最大。关于重度 AKI，GBC 算法的 AUC 明显高于其他 4 种 ML 模型（均 P<0.05）。尽管 GBC（0.86，95%CI：0.808，0.902）与传统逻辑回归（0.803，95%CI：0.746，0.852）之间的 AUC 无显著差异（P=0.173），但 GBC 的敏感性、准确性和 Youden 指数均高于传统 LR。值得注意的是，SHAP 分析表明，术前血清肌酐、高血脂、降脂药和辅助通气时间一直是术后 AKI 和重度 AKI 的前 5 个重要预测因素。
结论：逻辑回归和 GBC 算法在预测 PO-AKI 和重度 AKI 方面表现出中等至良好的区分度和较高的性能。模型解释确定了预测的关键因素，这可能有助于指导临床干预。
Heart Surg Forum. 2023-10-25
Zhonghua Wei Zhong Bing Ji Jiu Yi Xue. 2022-11
Pediatr Nephrol. 2024-4
J Clin Anesth. 2022-6
Nat Mach Intell. 2020-1
Zotero 插件
