What question did this study set out to answer?

This study aims to improve patient selection for transarterial chemoembolization in HBV-related HCC with PVTT1 using machine learning.

March 7, 2026Open Access

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

Key Points

This study aims to improve patient selection for transarterial chemoembolization in HBV-related HCC with PVTT1 using machine learning.
Conducted a retrospective multicenter study involving data from 15 hospitals in China (2012-2021)
Developed a Random Survival Forest model to identify prognostic variables
Evaluated model performance using Area Under the Receiver Operating Characteristic Curve (AUC)
Performed Propensity Score Matching to adjust for bias in survival comparisons
Identified tumor size, tumor number, AST, INR, and age as key predictors in the TACE-PVTT1 group
No significant survival difference was found between low-risk TACE-PVTT1 patients and those without PVTT (P = 0.19)
Significant survival advantage for TACE over sorafenib in patients with PVTT1

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 challenging disease.

Bookmark

View Full Paper