Lui Thomas Ka Luen, Cheung Ka Shing, Leung Wai Keung
Department of Medicine, University of Hong Kong, 4/F, Professorial Block, Queen Mary Hospital, 102 Pokfulam Road, Hong Kong, China.
Hepatol Int. 2022 Aug;16(4):879-891. doi: 10.1007/s12072-022-10370-3. Epub 2022 Jul 2.
Immunotherapy is a new promising treatment for patients with advanced hepatocellular carcinoma (HCC), but is costly and potentially associated with considerable side effects. This study aimed to evaluate the role of machine learning (ML) models in predicting the 1-year cancer-related mortality in advanced HCC patients treated with immunotherapy.
395 HCC patients who had received immunotherapy (including nivolumab, pembrolizumab or ipilimumab) between 2014 and 2019 in Hong Kong were included. The whole data sets were randomly divided into training (n = 316) and internal validation (n = 79) set. The data set, including 47 clinical variables, was used to construct six different ML models in predicting the risk of 1-year mortality. The performances of ML models were measured by the area under receiver operating characteristic curve (AUC) and their performances were compared with C-Reactive protein and Alpha Fetoprotein in ImmunoTherapY score (CRAFITY) and albumin-bilirubin (ALBI) score. The ML models were further validated with an external cohort between 2020 and 2021.
The 1-year cancer-related mortality was 51.1%. Of the six ML models, the random forest (RF) has the highest AUC of 0.92 (95% CI 0.87-0.98), which was better than logistic regression (0.82, p = 0.01) as well as the CRAFITY (0.68, p < 0.01) and ALBI score (0.84, p = 0.04). RF had the lowest false positive (2.0%) and false negative rate (5.2%), and performed better than CRAFITY score in the external validation cohort (0.91 vs 0.66, p < 0.01). High baseline AFP, bilirubin and alkaline phosphatase were three common risk factors identified by all ML models.
ML models could predict 1-year cancer-related mortality in HCC patients treated with immunotherapy, which may help to select patients who would benefit from this treatment.
免疫疗法是晚期肝细胞癌（HCC）患者一种新的有前景的治疗方法，但成本高昂且可能伴有相当多的副作用。本研究旨在评估机器学习（ML）模型在预测接受免疫疗法的晚期HCC患者1年癌症相关死亡率中的作用。
纳入2014年至2019年期间在香港接受免疫疗法（包括纳武单抗、派姆单抗或伊匹木单抗）的395例HCC患者。将整个数据集随机分为训练集（n = 316）和内部验证集（n = 79）。该数据集包括47个临床变量，用于构建六个不同的ML模型以预测1年死亡率风险。ML模型的性能通过受试者操作特征曲线下面积（AUC）来衡量，并将其性能与免疫治疗评分（CRAFITY）中的C反应蛋白和甲胎蛋白以及白蛋白-胆红素（ALBI）评分进行比较。ML模型在2020年至2021年期间通过外部队列进一步验证。
1年癌症相关死亡率为51.1%。在六个ML模型中，随机森林（RF）的AUC最高，为0.92（95%CI 0.87 - 0.98），优于逻辑回归（0.82，p = 0.01）以及CRAFITY（0.68，p < 0.01）和ALBI评分（0.84，p = 0.04）。RF的假阳性率（2.0%）和假阴性率最低（5.2%），并且在外部验证队列中表现优于CRAFITY评分（0.91对0.66，p < 0.01）。高基线甲胎蛋白、胆红素和碱性磷酸酶是所有ML模型确定的三个常见风险因素。
ML模型可以预测接受免疫疗法的HCC患者1年癌症相关死亡率，这可能有助于选择将从该治疗中获益的患者。
