Yan Yun, Gong Hairong, Hu Jie, Wu Di, Zheng Ziyu, Wang Lini, Lei Chong
Department of Anesthesiology and Perioperative Medicine, Xijing Hospital, The Fourth Military Medical University, Xi'an, China.
Department of Critical Care Medicine, the First Medical Centre, Chinese PLA General Hospital, Beijing, China.
Front Cardiovasc Med. 2023 Mar 7;10:1094997. doi: 10.3389/fcvm.2023.1094997. eCollection 2023.
Acute kidney injury (AKI) is a relevant complication after cardiac surgery and is associated with significant morbidity and mortality. Existing risk prediction tools have certain limitations and perform poorly in the Chinese population. We aimed to develop prediction models for AKI after valvular cardiac surgery in the Chinese population.
Models were developed from a retrospective cohort of patients undergoing valve surgery from December 2013 to November 2018. Three models were developed to predict all-stage, or moderate to severe AKI, as diagnosed according to Kidney Disease: Improving Global Outcomes (KDIGO) based on patient characteristics and perioperative variables. Models were developed based on lasso logistics regression (LLR), random forest (RF), and extreme gradient boosting (XGboost). The accuracy was compared among three models and against the previously published reference AKICS score.
A total of 3,392 patients (mean [SD] age, 50.1 [11.3] years; 1787 [52.7%] male) were identified during the study period. The development of AKI was recorded in 50.5% of patients undergoing valve surgery. In the internal validation testing set, the LLR model marginally improved discrimination (C statistic, 0.7; 95% CI, 0.66-0.73) compared with two machine learning models, RF (C statistic, 0.69; 95% CI, 0.65-0.72) and XGBoost (C statistic, 0.66; 95% CI, 0.63-0.70). A better calibration was also found in the LLR, with a greater net benefit, especially for the higher probabilities as indicated in the decision curve analysis. All three newly developed models outperformed the reference AKICS score.
Among the Chinese population undergoing CPB-assisted valvular cardiac surgery, prediction models based on perioperative variables were developed. The LLR model demonstrated the best predictive performance was selected for predicting all-stage AKI after surgery.
Trial registration: Clinicaltrials.gov, NCT04237636.
急性肾损伤（AKI）是心脏手术后的一种相关并发症，与显著的发病率和死亡率相关。现有的风险预测工具存在一定局限性，在中国人群中表现不佳。我们旨在开发中国人群心脏瓣膜手术后AKI的预测模型。
模型是根据2013年12月至2018年11月接受瓣膜手术的患者的回顾性队列开发的。根据患者特征和围手术期变量，开发了三个模型来预测根据改善全球肾脏病预后组织（KDIGO）诊断的全阶段或中度至重度AKI。模型基于套索逻辑回归（LLR）、随机森林（RF）和极端梯度提升（XGboost）开发。比较了三个模型之间以及与先前发表的参考AKICS评分的准确性。
在研究期间共识别出3392例患者（平均[标准差]年龄，50.1[11.3]岁；1787例[52.7%]为男性）。瓣膜手术患者中50.5%记录了AKI的发生。在内部验证测试集中，与两种机器学习模型RF（C统计量，0.69；95%CI，0.65 - 0.72）和XGBoost（C统计量，0.66；95%CI，0.63 - 0.70）相比，LLR模型在区分能力上略有提高（C统计量，0.7；95%CI，0.66 - 0.73）。在LLR中还发现了更好的校准，具有更大的净效益，特别是在决策曲线分析中显示的较高概率时。所有三个新开发的模型均优于参考AKICS评分。
在接受体外循环辅助心脏瓣膜手术的中国人群中，开发了基于围手术期变量的预测模型。选择表现出最佳预测性能的LLR模型来预测术后全阶段AKI。
试验注册：Clinicaltrials.gov，NCT04237636。
