An Chao, Yang Hongcai, Yu Xiaoling, Han Zhi-Yu, Cheng Zhigang, Liu Fangyi, Dou Jianping, Li Bing, Li Yansheng, Li Yichao, Yu Jie, Liang Ping
Department of Ultrasound, PLA Medical College & 5th Medical Center of Chinese PLA General Hospital, Beijing, 100853, People's Republic of China.
School of Medicine, Nankai University, Tianjin, People's Republic of China.
J Hepatocell Carcinoma. 2022 Jul 28;9:671-684. doi: 10.2147/JHC.S358197. eCollection 2022.
Early recurrence (ER) presents a challenge for the survival prognosis of patients with hepatocellular carcinoma (HCC). The aim of this study was to investigate machine learning (ML) models using clinical data for predicting ER after microwave ablation (MWA).
Between August 2005 and December 2019, 1574 patients with early-stage HCC underwent MWA at four hospitals were reviewed. Then, 36 clinical data points per patient were collected, and the patients were assigned to the training, internal, and external validation set. Apart from traditional logistic regression (LR), three ML models-random forest, support vector machine, and eXtreme Gradient Boosting (XGBoost)-were built and validated for their predictive ability with the area under ROC curve (AUC). Algorithms such as SHapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanations (LIME) were used to realize their interpretability.
The three ML models all outperformed LR ( < 0.001 for all) in predictive ability. When nine variables (tumor number, platelet, α-fetoprotein, comorbidity score, white blood cell, cholinesterase, prothrombin time, neutrophils, and etiology) were extracted simultaneously using recursive feature elimination with cross-validation, the XGBoost model achieved the best discrimination among all models, with an AUC value 0.75 (95% CI [confidence interval]: 0.72-0.78) in the training set, 0.74 (95% CI: 0.69-0.80) in the internal validation set, and 0.76 (95% CI: 0.70-0.82) in the external validation set, and it was interpreted depending on the visualization of risk factors by the SHAP and LIME algorithms. The predictive system of post-ablation recurrence risk stratification was provided on online (http://114.251.235.51:8001/) based on XGboost analysis.
The XGBoost model based on clinical data can effectively predict ER risk after MWA, which can contribute to surveillance, prevention, and treatment strategies for HCC.
早期复发（ER）对肝细胞癌（HCC）患者的生存预后构成挑战。本研究旨在探讨使用临床数据的机器学习（ML）模型来预测微波消融（MWA）后的早期复发。
回顾了2005年8月至2019年12月期间在四家医院接受MWA的1574例早期HCC患者。然后，收集每位患者的36个临床数据点，并将患者分配到训练集、内部验证集和外部验证集。除了传统的逻辑回归（LR）外，还构建了三种ML模型——随机森林、支持向量机和极端梯度提升（XGBoost），并通过ROC曲线下面积（AUC）验证其预测能力。使用诸如SHapley加性解释（SHAP）和局部可解释模型无关解释（LIME）等算法来实现其可解释性。
三种ML模型在预测能力上均优于LR（所有P均<0.001）。当使用带交叉验证的递归特征消除法同时提取九个变量（肿瘤数量、血小板、甲胎蛋白、合并症评分、白细胞、胆碱酯酶、凝血酶原时间、中性粒细胞和病因）时，XGBoost模型在所有模型中具有最佳的区分能力，在训练集中AUC值为0.75（95%置信区间[CI]：0.72 - 0.78），在内部验证集中为0.74（95%CI：0.69 - 0.80），在外部验证集中为0.76（95%CI：0.70 - 0.82），并且通过SHAP和LIME算法对危险因素的可视化进行了解释。基于XGBoost分析在网上（http://114.251.235.51:8001/）提供了消融后复发风险分层的预测系统。
基于临床数据的XGBoost模型可有效预测MWA后的早期复发风险，这有助于HCC的监测、预防和治疗策略。
