Machine Learning to Improve Prognosis Prediction of Early Hepatocellular Carcinoma After Surgical Resection.
Machine Learning to Improve Prognosis Prediction of Early Hepatocellular Carcinoma After Surgical Resection.
复制标题
机器学习以改善手术切除后早期肝细胞癌的预后预测。
DOI：
10.2147/jhc.s320172
复制
发表时间：
2021
影响因子：
4.1
通讯作者：
Wang XH
中科院分区：
文献类型：
--
作者：
Ji GW;Fan Y;Sun DW;Wu MY;Wang K;Li XC;Wang XH
早期肝细胞癌（EHCC）患者需要更好的预后预测来分层，以优化辅助治疗的选择。我们的目标是开发一种基于机器学习（ML）的模型，根据现成的临床数据预测EHCC肝切除术后的生存。我们分析了来自监测、流行病学和最终结果（SEER）项目的手术切除EHCC（肿瘤≤5cm，无肝外疾病或主要血管侵犯的证据）患者的数据，以训练和内部验证梯度增强ML模型来预测疾病特异性生存（DSS）。我们使用来自两家中国机构的数据对ML模型进行了外部测试。在SEER-Medicare数据库中，接受切除治疗的患者通过倾向评分与接受移植治疗的患者相匹配。本研究共纳入2778例接受切除治疗的EHCC患者，其中训练/验证组（SEER） 1899例，测试组（中文）879例。ML模型由8个协变量（年龄、种族、α胎蛋白、肿瘤大小、多灶性、血管侵袭、组织学分级和纤维化评分）组成，预测DSS的C-Statistics值为>.72，优于研究队列中提出的分期系统。ML模型可以将10年DSS从低风险组的70%到高风险组的5%进行分层。与低风险亚组相比，倾向评分匹配前后接受移植的EHCC患者未观察到显著的生存获益。在大规模数据集上训练的机器学习模型在个体尺度上具有良好的预测性能。这样的模型很容易整合到临床实践中，并且在讨论治疗策略时很有价值。
Improved prognostic prediction is needed to stratify patients with early hepatocellular carcinoma (EHCC) to refine selection of adjuvant therapy. We aimed to develop a machine learning (ML)-based model to predict survival after liver resection for EHCC based on readily available clinical data. We analyzed data of surgically resected EHCC (tumor≤5 cm without evidence of extrahepatic disease or major vascular invasion) patients from the Surveillance, Epidemiology, and End Results (SEER) Program to train and internally validate a gradient-boosting ML model to predict disease‐specific survival (DSS). We externally tested the ML model using data from 2 Chinese institutions. Patients treated with resection were matched by propensity score to those treated with transplantation in the SEER-Medicare database. A total of 2778 EHCC patients treated with resection were enrolled, divided into 1899 for training/validation (SEER) and 879 for test (Chinese). The ML model consisted of 8 covariates (age, race, alpha-fetoprotein, tumor size, multifocality, vascular invasion, histological grade and fibrosis score) and predicted DSS with C-Statistics >0.72, better than proposed staging systems across study cohorts. The ML model could stratify 10-year DSS ranging from 70% in low-risk subset to 5% in high-risk subset. Compared with low-risk subset, no remarkable survival benefits were observed in EHCC patients receiving transplantation before and after propensity score matching. An ML model trained on a large-scale dataset has good predictive performance at individual scale. Such a model is readily integrated into clinical practice and will be valuable in discussing treatment strategies.