Development of a novel combined nomogram model integrating Rad-score, age and ECOG to predict the survival of patients with hepatocellular carcinoma treated by transcatheter arterial chemoembolization

• Published in: Journal of gastrointestinal oncology 2022-08, Vol.13 (4), p.1889-1897
• Main Authors: Liu, Aiai, Liu, Bo, Duan, Xiaodong, Yang, Bo, Wang, Yiren, Dong, Ping, Zhou, Ping
• Format: Article
• Language: English
• Subjects: Original
• ISSN: 2078-6891; 2219-679X
• DOI: 10.21037/jgo-22-548

BackgroundLiver cancer is affecting more and more people's health. Transcatheter arterial chemoembolization (TACE) has become a routine treatment option, but the prognosis of patients is not optimistic. Effectively prediction of prognosis can provide clinicians with an objective basis for patient prognosis and timely adjustment of treatment strategies, thus improving the quality of patient survival. However, the current prediction methods have some limitations. Therefore, this study aims to develop a radiomics nomogram for predicting survival after TACE in patients with advanced hepatocellular carcinoma (HCC). MethodsSeventy advanced HCC patients treated with TACE were enrolled from January 2013 to July 2019. Clinical information included age, sex, and Eastern Cooperative Oncology Group (ECOG) score. Overall survival (OS) was confirmed by postoperative follow-up. Radiomics features were extracted using 3D Slicer (version 4.11.20210226) software, then obtain radiomics signature and calculate radiomics score (Rad-score) for each patient. Univariate and multivariate Cox regression were used to analyze the baseline clinical data of patients and establish clinical models. The obtained radiomics signature was incorporated into the clinical model to establish the radiomics nomogram. The predictive performance and calibration ability of the model were assessed by the area under the receiver operating characteristic (ROC) curve (AUC), C-index, and calibration curve. ResultsThree significant features were selected from 851 radiomics features by the least absolute shrinkage and selection operator (LASSO) Cox regression model to construct the radiomics signature, and were significantly correlated with overall survival (P