ORIGINAL RESEARCH article
Front. Oncol.
Sec. Gastrointestinal Cancers: Hepato Pancreatic Biliary Cancers
A Machine Learning Approach to Identify Optimal Candidates for Transarterial Chemoembolization in Unresectable HBV-related hepatocellular carcinoma complicated by First-Branch Portal Vein Tumor Thrombus: a multicenter study
Suo Zhao 1
Qi Zhang 1
Yichong Wang 2
YaJie Guo 3
Jiawei Song 4
Tenghui Han 5
Huadong Zhao 6
Yuheng Zhang 6
Chunzhi Yuan 2
Xiuqin Li 2
Jun Zhu 2
Lin Zhao 1
1. The 983 Hospital of the Joint Logistics Support Force, Chinese People's Liberation Army, Tianjin, China
2. People's Liberation Army The Air Force Hospital of Southern Theatre Command, Guangzhou, China
3. Xijing Digestive Disease Hospital Fourth Military Medical University, Xi'an, China
4. Sichuan University, Chengdu, China
5. Wuhan University of Science and Technology, Wuhan, China
6. Air Force Medical University Tangdu Hospital, Xi'an, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Abstract
Background: Portal vein tumor thrombus (PVTT) is a critical factor influencing prognosis and treatment allocation for Hepatitis B virus (HBV)-related hepatocellular carcinoma (HCC). However, accurately selecting patients with unresectable HCC and first-order branch PVTT (PVTT1) who would benefit from transarterial chemoembolization (TACE) remains a significant clinical challenge. This study aimed to leverage machine learning to address this issue. Methods: We conducted a large-scale, retrospective multicenter study utilizing data from 15 tertiary hospitals in China (2012-2021). A Random Survival Forest (RSF) model was constructed to identify key prognostic variables and stratify risk among TACE-treated PVTT1 patients. Model performance was evaluated using the Area Under the Receiver Operating Characteristic Curve (AUC). To mitigate selection bias and confounding factors for survival comparisons, Propensity Score Matching (PSM) was performed. Results: Of the 3,948 patients enrolled, 763 constituted the TACE-PVTT1 group. The RSF model exhibited robust predictive accuracy for this group, identifying tumor size, tumor number, AST, INR, and age as the top five clinical predictors. Patients in the bottom risk-score tertile were classified as low-risk. Notably, the overall survival (OS) of this low-risk TACE-PVTT1 group was not significantly different from that of the 3,073 TACE-PVTT0 patients (P=0.19), a finding that was maintained after PSM (P=0.54). A multivariate Cox analysis confirmed that in this low-risk context, PVTT1 status was not a significant prognostic factor (P=0.08575). Additionally, TACE conferred a significant survival advantage over sorafenib in patients with PVTT1. Conclusion: The integrated application of RSF and PSM can effectively identify low-risk candidates for TACE among patients with unresectable HCC and PVTT1. Our findings provide strong evidence that for this carefully selected patient subgroup, TACE offers survival outcomes comparable to those for patients without PVTT, highlighting the clinical utility of machine learning in guiding treatment decisions for this 3 challenging disease.
Summary
Keywords
First-Branch Portal Vein Tumor Thrombus, HBV-related hepatocellular carcinoma, machine learning, Propensity score matching, Random survival forest, Transarterial chemoembolization
Received
12 December 2025
Accepted
17 February 2026
Copyright
© 2026 Zhao, Zhang, Wang, Guo, Song, Han, Zhao, Zhang, Yuan, Li, Zhu and Zhao. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Lin Zhao
Disclaimer
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.