Department of Anesthesiology, The Third Affiliated Hospital of Sun Yat-Sen University, No. 600 Tianhe Road, Guangzhou, Guangdong, China.
Guangzhou AID Cloud Technology Co., LTD, Guangzhou, Guangdong, China.
J Transl Med. 2021 Jul 28;19(1):321. doi: 10.1186/s12967-021-02990-4.
Early prediction of acute kidney injury (AKI) after liver transplantation (LT) facilitates timely recognition and intervention. We aimed to build a risk predictor of post-LT AKI via supervised machine learning and visualize the mechanism driving within to assist clinical decision-making.
Data of 894 cases that underwent liver transplantation from January 2015 to September 2019 were collected, covering demographics, donor characteristics, etiology, peri-operative laboratory results, co-morbidities and medications. The primary outcome was new-onset AKI after LT according to Kidney Disease Improving Global Outcomes guidelines. Predicting performance of five classifiers including logistic regression, support vector machine, random forest, gradient boosting machine (GBM) and adaptive boosting were respectively evaluated by the area under the receiver-operating characteristic curve (AUC), accuracy, F1-score, sensitivity and specificity. Model with the best performance was validated in an independent dataset involving 195 adult LT cases from October 2019 to March 2021. SHapley Additive exPlanations (SHAP) method was applied to evaluate feature importance and explain the predictions made by ML algorithms.
430 AKI cases (55.1%) were diagnosed out of 780 included cases. The GBM model achieved the highest AUC (0.76, CI 0.70 to 0.82), F1-score (0.73, CI 0.66 to 0.79) and sensitivity (0.74, CI 0.66 to 0.8) in the internal validation set, and a comparable AUC (0.75, CI 0.67 to 0.81) in the external validation set. High preoperative indirect bilirubin, low intraoperative urine output, long anesthesia time, low preoperative platelets, and graft steatosis graded NASH CRN 1 and above were revealed by SHAP method the top 5 important variables contributing to the diagnosis of post-LT AKI made by GBM model.
Our GBM-based predictor of post-LT AKI provides a highly interoperable tool across institutions to assist decision-making after LT.
肝移植（LT）后急性肾损伤（AKI）的早期预测有助于及时识别和干预。我们旨在通过有监督的机器学习建立 LT 后 AKI 的风险预测器，并可视化驱动机制，以协助临床决策。
收集了 2015 年 1 月至 2019 年 9 月期间接受肝移植的 894 例患者的数据，包括人口统计学、供体特征、病因、围手术期实验室结果、合并症和药物治疗。主要结局是根据肾脏病改善全球结局指南（KDIGO）定义的 LT 后新发 AKI。通过受试者工作特征曲线下面积（AUC）、准确性、F1 评分、敏感性和特异性，分别评估包括逻辑回归、支持向量机、随机森林、梯度提升机（GBM）和自适应提升在内的 5 种分类器的预测性能。在 2019 年 10 月至 2021 年 3 月期间包含 195 例成人 LT 病例的独立数据集上验证表现最佳的模型。应用 SHapley Additive exPlanations（SHAP）方法评估特征重要性并解释 ML 算法的预测。
在纳入的 780 例患者中，430 例（55.1%）被诊断为 AKI 病例。GBM 模型在内部验证集中实现了最高 AUC（0.76，CI 0.70 至 0.82）、F1 评分（0.73，CI 0.66 至 0.79）和敏感性（0.74，CI 0.66 至 0.8），在外部验证集中 AUC 相当（0.75，CI 0.67 至 0.81）。SHAP 方法揭示了术前间接胆红素高、术中尿量低、麻醉时间长、术前血小板低以及脂肪变性分级为 NASH CRN 1 及以上的供体肝，是 GBM 模型诊断 LT 后 AKI 的前 5 个重要变量。
我们基于 GBM 的 LT 后 AKI 预测器为 LT 后决策提供了一种在机构间高度可互操作的工具。
