College of Information Science, Shanghai Ocean University, Shanghai, P.R. China.
Department of Cardiovascular Surgery, Qilu Hospital of Shandong University, Jinan, Shandong, P.R. China.
BMC Med Inform Decis Mak. 2023 Nov 23;23(1):270. doi: 10.1186/s12911-023-02376-0.
Acute kidney injury (AKI) after coronary artery bypass grafting (CABG) surgery is associated with poor outcomes. The objective of this study was to apply a new machine learning (ML) method to establish prediction models of AKI after CABG.
A total of 2,780 patients from two medical centers in East China who underwent primary isolated CABG were enrolled. The dataset was randomly divided for model training (80%) and model testing (20%). Four ML models based on LightGBM, Support vector machine (SVM), Softmax and random forest (RF) algorithms respectively were established in Python. A total of 2,051 patients from two other medical centers were assigned to an external validation group to verify the performances of the ML prediction models. The models were evaluated using the area under the receiver operating characteristics curve (AUC), Hosmer-Lemeshow goodness-of-fit statistic, Bland-Altman plots, and decision curve analysis. The outcome of the LightGBM model was interpreted using SHapley Additive exPlanations (SHAP).
The incidence of postoperative AKI in the modeling group was 13.4%. Similarly, the incidence of postoperative AKI of the two medical centers in the external validation group was 8.2% and 13.6% respectively. LightGBM performed the best in predicting, with an AUC of 0.8027 in internal validation group and 0.8798 and 0.7801 in the external validation group. The SHAP revealed the top 20 predictors of postoperative AKI ranked according to the importance, and the top three features on prediction were the serum creatinine in the first 24 h after operation, the last preoperative Scr level, and body surface area.
This study provides a LightGBM predictive model that can make accurate predictions for AKI after CABG surgery. The LightGBM model shows good predictive ability in both internal and external validation. It can help cardiac surgeons identify high-risk patients who may experience AKI after CABG surgery.
冠状动脉旁路移植术（CABG）后急性肾损伤（AKI）与不良预后相关。本研究旨在应用一种新的机器学习（ML）方法建立 CABG 术后 AKI 的预测模型。
共纳入华东地区 2 家中心 2780 例行择期 CABG 的患者。数据集随机分为模型训练（80%）和模型测试（20%）。分别采用 LightGBM、支持向量机（SVM）、Softmax 和随机森林（RF）算法建立基于 4 种 ML 的预测模型。来自另外 2 家中心的 2051 例患者被分配到外部验证组，以验证 ML 预测模型的性能。采用受试者工作特征曲线下面积（AUC）、Hosmer-Lemeshow 拟合优度统计、Bland-Altman 图和决策曲线分析评估模型。通过 SHapley Additive exPlanations（SHAP）解释 LightGBM 模型的结果。
建模组术后 AKI 发生率为 13.4%。同样，外部验证组 2 家中心术后 AKI 发生率分别为 8.2%和 13.6%。LightGBM 在预测中表现最佳，内部验证组 AUC 为 0.8027，外部验证组分别为 0.8798 和 0.7801。SHAP 显示了根据重要性排序的术后 AKI 前 20 个预测因子，预测的前三个特征是术后 24 小时内的血清肌酐、最后一次术前 Scr 水平和体表面积。
本研究提供了一种 LightGBM 预测模型，可对 CABG 术后 AKI 进行准确预测。LightGBM 模型在内部和外部验证中均表现出良好的预测能力。它可以帮助心脏外科医生识别可能在 CABG 手术后发生 AKI 的高危患者。
