Junwei Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Junwei Chen has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Chao An
Department of Minimally Invasive Interventional Therapy, Sun Yat-Sen University Cancer Center, Guangzhou, China
2 shared publications Chengzhi Li
Department of Interventional Radiology and Vascular Surgery, The First Affiliated Hospital of Jinan University, Guangzhou, P. R. China
1 shared publication- Chengzhi Li
Department of Interventional Radiology and Vascular Surgery, The First Affiliated Hospital of Jinan University, Guangzhou, People’s Republic of China
1 shared publication - Dong Yan
Cancer Center, Beijing Luhe Hospital, Capital Medical University, China
1 shared publication - Fengtao Zhang
College of Life Science and Technology, Jinan University, Guangzhou 510632, China
1 shared publication - Guolian Zhu
Department of Interventional Therapy, Cancer Prevention and Treatment Center, Shantou Overseas Chinese Hospital (Chenghai District People’s Hospital), Shantou, Guangdong, P. R. China
1 shared publication
Latest Publications
- Open Access
- 23 September 2025
- Published by Wolters Kluwer Health in International Journal of Surgery
- Vol. 112 (1) , 1164-1176
Identification and validation of an explainable machine learning model for hepatocellular carcinoma at high risk: a retrospective multicenter cohort study
Background: Currently, there is still a lack of noninvasive, automated, and accurate machine learning (ML) model for prognostic risk stratification of high-risk hepatocellular carcinoma (hHCC) after transarterial chemoembolization (TACE). Purpose: To develop and test an ML-based model that integrates various clinical variables for prediction of early recurrence (ER, defined as recurrence within 24 months after treatment) after TACE for hHCC. Methods: From May 2008 to October 2022, consecutive patients with unresectable HCC who underwent initial TACE were reviewed at multicenter. We input 39 preoperative and 5 treatment-related variables into five ML-based models for ER prediction. Furthermore, we compared their performances using area under the receiver operating characteristic curve (AUC) with DeLong test between these ML models and the major staging systems including Barcelona Clinic Liver Cancer, China National Liver Cancer, American Joint Committee on Cancer, Japan Society of Hepatology, and Hong Kong Liver Cancer. Overall survival (OS) and recurrence-free survival (RFS) were analyzed using the Kaplan–Meier method with log-rank tests. Results: A total of 2068 eligible patients with hHCC were categorized into the training set ( n = 1220), the internal test set ( n = 306), and the external test set ( n = 542). ER rate was found in 78.4%, 78.8 %, and 62.5% of patients in three sets. Among all ML models, the eXtreme gradient boosting (XGBoost) model using top seven variables yielded the highest AUC of 0.888 in the internal test set and 0.854 in the external test set. Furthermore, it yielded better discriminatory ability for RFS with higher time-dependent AUC than all major staging systems (DeLong test, all P < 0.001). Kaplan–Meier analysis revealed significant OS and RFS risk stratification using the XGBoost model in three sets, respectively. Conclusion: The XGBoost model demonstrated superior predictive performance compared with other four ML models and all clinical staging systems in identifying ER, which may support individualized TACE management by guiding therapy selection.
- 23 September 2025
- Published by Wolters Kluwer Health in International Journal of Surgery
- Vol. 112 (1) , 1164-1176
Open AccessIdentification and validation of an explainable machine learning model for hepatocellular carcinoma at high risk: a retrospective multicenter cohort study
Background: Currently, there is still a lack of noninvasive, automated, and accurate machine learning (ML) model for prognostic risk stratification of high-risk hepatocellular carcinoma (hHCC) after transarterial chemoembolization (TACE). Purpose: To develop and test an ML-based model that integrates various clinical variables for prediction of early recurrence (ER, defined as recurrence within 24 months after treatment) after TACE for hHCC. Methods: From May 2008 to October 2022, consecutive patients with unresectable HCC who underwent initial TACE were reviewed at multicenter. We input 39 preoperative and 5 treatment-related variables into five ML-based models for ER prediction. Furthermore, we compared their performances using area under the receiver operating characteristic curve (AUC) with DeLong test between these ML models and the major staging systems including Barcelona Clinic Liver Cancer, China National Liver Cancer, American Joint Committee on Cancer, Japan Society of Hepatology, and Hong Kong Liver Cancer. Overall survival (OS) and recurrence-free survival (RFS) were analyzed using the Kaplan–Meier method with log-rank tests. Results: A total of 2068 eligible patients with hHCC were categorized into the training set ( n = 1220), the internal test set ( n = 306), and the external test set ( n = 542). ER rate was found in 78.4%, 78.8 %, and 62.5% of patients in three sets. Among all ML models, the eXtreme gradient boosting (XGBoost) model using top seven variables yielded the highest AUC of 0.888 in the internal test set and 0.854 in the external test set. Furthermore, it yielded better discriminatory ability for RFS with higher time-dependent AUC than all major staging systems (DeLong test, all P < 0.001). Kaplan–Meier analysis revealed significant OS and RFS risk stratification using the XGBoost model in three sets, respectively. Conclusion: The XGBoost model demonstrated superior predictive performance compared with other four ML models and all clinical staging systems in identifying ER, which may support individualized TACE management by guiding therapy selection.
- Open Access
- 8 May 2024
- Published by Springer Nature in Hepatology International
- Vol. 18 (4) , 1286-1298
Hepatic artery infusion chemotherapy combined with camrelizumab plus rivoceranib for hepatocellular carcinoma with portal vein tumor thrombosis: a multicenter propensity score-matching analysis
Background: Portal vein tumor thrombosis (PVTT) signifies late-stage hepatocellular carcinoma (HCC) with high-risk progression and poor prognosis. As a standard treatment, sorafenib monotherapy has limited the efficacy in managing HCC with PVTT. Currently, both hepatic arterial infusion chemotherapy (HAIC) and the combination of camrelizumab and rivoceranib have shown favorable survival benefits for advanced HCC, surpassing the standard sorafenib treatment. In this study, we investigate the safety and efficacy of HAIC combined with camrelizumab and rivoceranib in treating HCC patients with PVTT. Methods: From January 2020 to December 2021, HCC patients with PVTT, who received either a triple regime of HAIC combined with camrelizumab and rivoceranib or a dual regime of camrelizumab and rivoceranib as their first-line treatment, were reviewed for eligibility at four hospital centers in China. To balance any intergroup differences, propensity score matching (PSM) was applied. The aim of this study is to compare the efficacy of the dual and triple combination treatment regimens based on survival prognosis and tumor response and evaluate the safety based on the occurrence of adverse reactions. Result: In this study, a total of 411 patients who received either the triple treatment regime (HAIC combined with camrelizumab plus rivoceranib, referred to as the HAICCR group, n = 292) or the dual treatment regime (camrelizumab combined with rivoceranib, referred to as the CR group, n = 119) between January 2020 and December 2021 were included. The results showed that the HAICCR group exhibited significantly better overall survival (mOS: 19.60 months vs. 11.50 months, p < 0.0001) and progression-free survival (mPFS: 10.0 months vs. 5.6 months, p < 0.0001) compared to the CR group in the overall cohort. Moreover, the HAICCR group also had a significantly higher ORR (objective response rate, 55.5% vs. 42.0%, p = 0.013) and DCR (disease control rate, 89.0% vs. 79.0%) compared to the CR group. After PSM, a final matched cohort of 83 pairs was obtained, and the survival benefits were consistent in this cohort as well (mOS: 18.70 months vs. 11.0 months, p < 0.0001; mPFS: 10.0 months vs. 5.6 months, p < 0.0001). However, there was no significant difference in the ORR between the triple and dual combination regimes. Univariate and multivariate analysis showed that CTP (Child–Turcotte–Pugh) stage, ALBI (albumin–bilirubin index) grade, tumor number, and treatment regime were significant risk factors affecting overall survival, while AFP (α-fetoprotein) level, tumor number, metastasis, and treatment regime were significant risk factors affecting progression-free survival. As for safety, hypertension and hand–foot syndrome were the two most common adverse reactions in both groups, with no significant difference in the occurrence of adverse reactions between the two groups (p < 0.05). Conclusion: In the context of advanced HCC patients with PVTT, the combination regime of HAIC and camrelizumab plus rivoceranib demonstrates more excellent capacity for prolonging survival and offers a well-tolerated safety compared to the CR dual therapy approach. This triple regime represents a therapeutic modality of broad prospects and vast potential for HCC patients with PVTT.
- 8 May 2024
- Published by Springer Nature in Hepatology International
- Vol. 18 (4) , 1286-1298
Open AccessHepatic artery infusion chemotherapy combined with camrelizumab plus rivoceranib for hepatocellular carcinoma with portal vein tumor thrombosis: a multicenter propensity score-matching analysis
Background: Portal vein tumor thrombosis (PVTT) signifies late-stage hepatocellular carcinoma (HCC) with high-risk progression and poor prognosis. As a standard treatment, sorafenib monotherapy has limited the efficacy in managing HCC with PVTT. Currently, both hepatic arterial infusion chemotherapy (HAIC) and the combination of camrelizumab and rivoceranib have shown favorable survival benefits for advanced HCC, surpassing the standard sorafenib treatment. In this study, we investigate the safety and efficacy of HAIC combined with camrelizumab and rivoceranib in treating HCC patients with PVTT. Methods: From January 2020 to December 2021, HCC patients with PVTT, who received either a triple regime of HAIC combined with camrelizumab and rivoceranib or a dual regime of camrelizumab and rivoceranib as their first-line treatment, were reviewed for eligibility at four hospital centers in China. To balance any intergroup differences, propensity score matching (PSM) was applied. The aim of this study is to compare the efficacy of the dual and triple combination treatment regimens based on survival prognosis and tumor response and evaluate the safety based on the occurrence of adverse reactions. Result: In this study, a total of 411 patients who received either the triple treatment regime (HAIC combined with camrelizumab plus rivoceranib, referred to as the HAICCR group, n = 292) or the dual treatment regime (camrelizumab combined with rivoceranib, referred to as the CR group, n = 119) between January 2020 and December 2021 were included. The results showed that the HAICCR group exhibited significantly better overall survival (mOS: 19.60 months vs. 11.50 months, p < 0.0001) and progression-free survival (mPFS: 10.0 months vs. 5.6 months, p < 0.0001) compared to the CR group in the overall cohort. Moreover, the HAICCR group also had a significantly higher ORR (objective response rate, 55.5% vs. 42.0%, p = 0.013) and DCR (disease control rate, 89.0% vs. 79.0%) compared to the CR group. After PSM, a final matched cohort of 83 pairs was obtained, and the survival benefits were consistent in this cohort as well (mOS: 18.70 months vs. 11.0 months, p < 0.0001; mPFS: 10.0 months vs. 5.6 months, p < 0.0001). However, there was no significant difference in the ORR between the triple and dual combination regimes. Univariate and multivariate analysis showed that CTP (Child–Turcotte–Pugh) stage, ALBI (albumin–bilirubin index) grade, tumor number, and treatment regime were significant risk factors affecting overall survival, while AFP (α-fetoprotein) level, tumor number, metastasis, and treatment regime were significant risk factors affecting progression-free survival. As for safety, hypertension and hand–foot syndrome were the two most common adverse reactions in both groups, with no significant difference in the occurrence of adverse reactions between the two groups (p < 0.05). Conclusion: In the context of advanced HCC patients with PVTT, the combination regime of HAIC and camrelizumab plus rivoceranib demonstrates more excellent capacity for prolonging survival and offers a well-tolerated safety compared to the CR dual therapy approach. This triple regime represents a therapeutic modality of broad prospects and vast potential for HCC patients with PVTT.