Rodriguez Isaac, Vellala Abhinay, Itzel Timo, Daza Jimmy, Vácha Michael, Chang De-Hua, Debic Manuel, Dill Michael T, Seidensticker Max, Mayerle Julia, Munker Stefan, Schoenberg Stefan O, Müller Lukas, Galle Peter R, Weinmann Arndt, Tamandl Dietmar, Pinter Matthias, Scheiner Bernhard, Weiss Christel, Pech Maciej, Sinner Friedrich, Keitel Verena, Venerito Marino, Ebert Matthias Philip, Teufel Andreas, Froelich Matthias F
Division of Hepatology, Division of Clinical Bioinformatics, Department of Medicine II, Medical Faculty Mannheim, Heidelberg University, D-68167 Mannheim, Germany.
Department of Radiology and Nuclear Medicine, Medical Faculty Mannheim, Heidelberg University, D-68167 Mannheim, Germany.
Oncol Lett. 2025 Aug 14;30(4):484. doi: 10.3892/ol.2025.15229. eCollection 2025 Oct.
Advanced hepatocellular carcinoma (HCC) treatment has evolved with the introduction of atezolizumab/bevacizumab, showing improved outcomes over sorafenib. However, the response varies among patients, particularly between viral and non-viral etiologies. The present study aimed to develop and evaluate multimodal prediction models combining quantitative imaging and clinical markers to predict the treatment response in patients with HCC. Between March 2020 and May 2023, patients with advanced HCC treated with atezolizumab/bevacizumab were retrospectively identified from six centers in Germany and Austria. Patients underwent baseline contrast-enhanced liver MRI and follow-up imaging to assess the therapy response. Machine learning models, including RandomForestClassifier, were developed for radiomics, clinical and combined datasets. Hyperparameter tuning was performed using RandomizedSearchCV, followed by cross-validation to evaluate model performance. The study included 103 patients, with 70 achieving disease control (DC) and 33 experiencing disease progression (PD). Key findings included significant differences in treatment response and progression-free survival between the DC and PD groups. The radiomics model, using 14 selected features, achieved 73.1% accuracy and a receiver operating characteristic (ROC) area under the curve (AUC) of 0.635 for the test set. The clinical model, with 4 selected features, achieved 73% accuracy and a ROC AUC of 0.649 for the test set. The combined model showed improved performance, with 69% accuracy and a ROC AUC of 0.753 for the test set. Hyperparameter tuning further enhanced the accuracy of the combined model to 80.1% and the ROC AUC to 0.771 for the test set. In conclusion, the hybrid model combining clinical and radiological data outperformed individual models, providing improved predictions of response to atezolizumab/bevacizumab in patients with HCC.
随着阿替利珠单抗/贝伐单抗的引入，晚期肝细胞癌（HCC）的治疗有了进展，与索拉非尼相比，疗效有所改善。然而，患者之间的反应存在差异，尤其是在病毒病因和非病毒病因之间。本研究旨在开发和评估结合定量成像和临床标志物的多模式预测模型，以预测HCC患者的治疗反应。在2020年3月至2023年5月期间，从德国和奥地利的六个中心回顾性识别接受阿替利珠单抗/贝伐单抗治疗的晚期HCC患者。患者接受基线对比增强肝脏MRI检查和随访成像，以评估治疗反应。针对放射组学、临床和联合数据集开发了包括随机森林分类器在内的机器学习模型。使用随机搜索交叉验证（RandomizedSearchCV）进行超参数调整，随后进行交叉验证以评估模型性能。该研究纳入了103例患者，其中70例实现疾病控制（DC），33例疾病进展（PD）。主要发现包括DC组和PD组在治疗反应和无进展生存期方面存在显著差异。放射组学模型使用14个选定特征，测试集的准确率达到73.1%，曲线下受试者操作特征（ROC）面积（AUC）为0.635。临床模型有4个选定特征，测试集的准确率达到73%，ROC AUC为0.649。联合模型表现更佳，测试集的准确率为69%，ROC AUC为0.753。超参数调整进一步将联合模型的准确率提高到80.1%，测试集的ROC AUC提高到0.771。总之，结合临床和放射学数据的混合模型优于单个模型，能更好地预测HCC患者对阿替利珠单抗/贝伐单抗的反应。
