目的和背景：本次荟萃分析的目的在于评估放射组学在经肝动脉化疗栓塞治疗（TACE）对肝细胞癌（HCC）的治疗反应（TR）和患者生存状态（SS）的预测价值，并为临床应用提供有利的证据。我们在PubMed、Embase、Cochrane图书馆和Web of Science等数据库中搜索，以纳入将放射组学应用于评估HCC TACE的TR和受影响患者的生存状态的文献，截至2023年7月12日。使用放射组学质量评分（RQS）方法对纳入文献的质量进行评估，并使用Stata15.0进行荟萃分析。共纳入24项研究进行分析。荟萃分析结果显示，基于放射组学的TR和SS预测的总体一致指数（C-index）分别为0.85和0.78。与放射组学模型和临床模型相比，联合放射组学临床模型在评估TACE相关的TR和SS方面表现最佳。在训练集和验证集中，TR的C-index分别为0.93和0.88，SS的C-index分别为0.84和0.80。这些数值均高于放射组学模型的TR分别为0.87和0.79，SS分别为0.79和0.70，以及临床模型的TR分别为0.71和0.66，SS分别为0.72和0.66。放射组学对HCC TACE疗效的预测模型表现出了令人满意的预测性能，而联合放射组学临床预测模型表现最佳。版权所有 © 2023 The Association of University Radiologists. Elsevier Inc. 发布，保留所有权利。

RATIONALE AND OBJECTIVES: This meta-analysis was aimed at evaluating the predictive value of radiomics in the context of transarterial chemoembolization (TACE) therapeutic response (TR) for hepatocellular carcinoma (HCC) and patients' survival status (SS) and providing favorable evidence for clinical application.We searched for literature in which radiomics was applied to assess the TR of TACE for HCC and the affected patients' survival status across PubMed, Embase, Cochrane Library and Web of Science until Jul 12, 2023. The quality of included literature was evaluated using a radiomics quality score (RQS) approach, and a meta-analysis was conducted using Stata15.0.Twenty-four studies were included in the analysis. The meta-analysis revealed that the overall concordance-index (C-index) based on radiomics for predicting the TR and SS with TACE was 0.85 and 0.78, respectively. The combined radiomics-clinical model provided the best performance in evaluating the TR and SS associated with TACE. The C-index was 0.93 and 0.88 for TR and 0.84 and 0.80 for SS, in the training and validation sets, respectively. These values were higher than the 0.87 and 0.79 for TR and 0.79 and 0.70 for SS, respectively with the radiomics model, and 0.71 and 0.66 for TR and 0.72 and 0.66 for SS, respectively with the clinical model.The radiomics prediction model for the efficacy of TACE in HCC showed a satisfactory prediction performance. The combined radiomics-clinic prediction model had the best performance.Copyright © 2023 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.