基于CT影像组学联合临床指标预测中晚期肝细胞癌靶免联合治疗疗效  

Predicting the Efficacy of Targeted and Immunotherapy Combined Treatment for Advanced Hepatocellular Carcinoma Based on CT Radiomics and Clinical Indicators

作　　者：何欣宇 韩雪晶 史中兴[1] 王佳会 崔立明[1] HE Xinyu;HAN Xuejing;SHI Zhongxing(Interventional Radiology Department,The Second Affiliated Hospital of Harbin Medical University Harbin,Heilongjiang Province 150086,P.R.China)

机构地区：[1]哈尔滨医科大学附属第二医院放射介入科,150086

出　　处：《临床放射学杂志》2025年第5期893-897,共5页Journal of Clinical Radiology

摘　　要：目的探讨结合CT影像组学和临床因素的预测模型对中晚期原发性肝癌患者靶免联合治疗疗效的评估价值。方法回顾性纳入101例中晚期肝细胞癌患者,分析其临床和影像学资料,分别构建预测模型。结果联合模型在训练集和测试集上均展现出最优的预测性能,曲线下面积分别为0.93和0.85,优于单一的影像组学模型和临床模型。结论结合CT影像组学和临床指标的联合模型可以有效预测中晚期肝细胞癌患者靶免联合治疗的疗效,为临床决策提供参考,并有望指导个体化治疗方案的选择。Objective This study aims to investigate the value of a predictive model that combines CT radiomics with clinical factors in evaluating the efficacy of target-immune combination therapy for patients with advanced primary liver cancer.Methods A retrospective analysis was conducted on 101 patients diagnosed with advanced hepatocellular carcinoma.Clinical data and CT imaging features were collected and analyzed to develop predictive models.The models were constructed using machine learning algorithms and were validated using a hold-out test set.Results The combined model,which integrated radiomic features from CT imaging with clinical variables,demonstrated the highest predictive accuracy.In the training set,the model achieved an area under the receiver operating characteristic curve(AUC)of 0.93,indicating a strong predictive capability.Similarly,in the test set,the model maintained a high AUC of 0.85,outperforming the radiomics-only model and the clinical factors-only model.The combined model also showed improved sensitivity and specificity in predicting treatment response.Conclusion The results of this study confirm the significant potential of a predictive model that merges CT radiomics with clinical information in assessing the therapeutic response to target-immune combination therapy in patients with advanced hepatocellular carcinoma.This integrated approach provides a more comprehensive and accurate tool for clinicians to predict treatment outcomes,which can be instrumental in guiding personalized treatment strategies.The model’s ability to integrate both imaging and clinical data offers a more nuanced understanding of the disease’s complexity and could lead to more effective and targeted interventions.

关 键 词：原发性肝癌 靶免联合治疗 影像组学 预测模型 疗效评估 

分 类 号：R735.7[医药卫生—肿瘤]