Computed tomography-based radiomics to predict early recurrence of hepatocellular carcinoma post-hepatectomy in patients background on cirrhosis
作者机构：Department of Hepatic SurgeryAnhui Provincial HospitalThe First Affiliated Hospital of USTCDivision of Life Science and MedicineUniversity of Science and Technology of ChinaHefei 230001Anhui ProvinceChina Department of Hepatic SurgeryAnhui Provincial Hospital Affiliated to Anhui Medical UniversityAnhui Medical UniversityHefei 230001Anhui ProvinceChina Department of Anorectal Surgerythe First People’s Hospital of HefeiHefei 230001Anhui ProvinceChina
出 版 物：《World Journal of Gastroenterology》 (世界胃肠病学杂志（英文版）)
年 卷 期：2024年第30卷第15期
页 面：2128-2142页
核心收录：
学科分类：1002[医学-临床医学] 100214[医学-肿瘤学] 10[医学]
基 金：Supported by Anhui Provincial Key Research and Development Plan No.202104j07020048
主 题：Machine learning Radiomics Hepatocellular carcinoma Cirrhosis Early recurrence Overall survival Computed tomography Prognosis Risk factor Delta-radiomics
摘 要：BACKGROUND The prognosis for hepatocellular carcinoma(HCC)in the presence of cirrhosis is unfavourable,primarily attributable to the high incidence of *** To develop a machine learning model for predicting early recurrence(ER)of posthepatectomy HCC in patients with cirrhosis and to stratify patients’overall survival(OS)based on the predicted risk of *** In this retrospective study,214 HCC patients with cirrhosis who underwent curative hepatectomy were *** feature selection was conducted using the least absolute shrinkage and selection operator and recursive feature elimination ***-radiologic features were selected through univariate and multivariate logistic regression *** machine learning methods were used for model comparison,aiming to identify the optimal *** model’s performance was evaluated using the receiver operating characteristic curve[area under the curve(AUC)],calibration,and decision curve ***,the Kaplan-Meier(K-M)curve was used to evaluate the stratification effect of the model on patient *** Within this study,the most effective predictive performance for ER of post-hepatectomy HCC in the background of cirrhosis was demonstrated by a model that integrated radiomics features and clinical-radiologic *** the training cohort,this model attained an AUC of 0.844,while in the validation cohort,it achieved a value of *** K-M curves illustrated that the combined model not only facilitated risk stratification but also exhibited significant discriminatory ability concerning patients’*** The combined model,integrating both radiomics and clinical-radiologic characteristics,exhibited excellent performance in HCC with *** K-M curves assessing OS revealed statistically significant differences.
维普期刊数据库