Answers are grounded in this paper and cite their sources.
Background The benefit of adjuvant chemotherapy (AC) for locoregionally advanced nasopharyngeal carcinoma (LA-NPC) is uncertain. We aimed to develop a model integrating post-treatment MRI radiomics and Epstein-Barr virus (EBV) DNA to identify patients who benefit from AC. Methods We retrospectively enrolled 267 patients with LA-NPC treated at a single institution. A radiomic-clinical signature (RCS) for predicting 2-year progression-free survival (PFS) was constructed using radiomic features extracted from post-concurrent chemoradiotherapy (CCRT) multi-sequence MRI and dynamic EBV DNA data. Model performance was evaluated using Harrell's concordance index (C-index). Patients were stratified into high- and low-risk subgroups based on the RCS, and the survival benefit of AC was assessed using Kaplan-Meier analysis. Results The cohort was randomly divided into training (n = 213) and testing (n = 54) sets. The fused RCS model achieved C-indices of 0.899 and 0.719 for predicting 2-year PFS in the training and testing sets, respectively, outperforming models using clinical (0.583) or radiomic (0.695) features alone. Risk stratification by the RCS identified low- and high-risk groups with significantly different survival outcomes (all p < 0.05). Subgroup analysis showed that AC significantly improved 2-year PFS only in the high-risk group (94.3% vs. 87.0%, p = 0.045), with no benefit observed in low-risk patients. Conclusions The RCS model effectively stratifies patients with LA-NPC and may guide personalized AC decisions by identifying high-risk patients likely to benefit. Trial registration Not applicable. This was a retrospective observational study and was not registered as a clinical trial.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: