Different prognostic values of plasma Epstein-Barr virus DNA and maximal standardized uptake value of 18F-FDG PET/CT for nasopharyngeal carcinoma patients with recurrence

Abstract

Purpose: To evaluate and compare the prognostic value of Epstein-Barr virus (EBV) DNA and maximal standard uptake values (SUVmax ) of 18F-fluoro-2-deoxy-D-glucose positron emission tomography (18F-FDG-PET) in subgroups of nasopharyngeal carcinoma (NPC) patients with locoregional or distant recurrence.

Patients and methods: A total of 194 patients with recurrent NPC (locoregional recurrence: 107, distant recurrence: 87) were enrolled. Patients took evidence of recurrence performed with 18F-FDG-PET and an EBV DNA test before salvage treatment. Clinical parameters, the status of EBV DNA and the value of SUVmax were used for survival analysis using the Kaplan-Meier method and the Cox proportional hazards regression model.

Results: In the subgroup of patients with locoregional recurrence, patients with SUVmax<8.65 had significantly better overall survival (OS) (P=0.005) compared with the patients with SUVmax ≥8.65. However, both elevated EBV DNA load (≥21,100 copies/ml) and distant SUVmax (≥13.55) were significantly associated with worse OS compared with the patients with EBV DNA <21,100 copies/ml or distant SUVmax <13.55 for the subgroup with distant recurrence (P=0.015 and P=0.006, respectively). The predictive ability of EBV DNA was superior to that of SUVmax (P=0.062). Multivariate analysis showed that SUVmax was only an independent prognostic factor for OS in patients with locoregional recurrence (P=0.042), whereas EBV DNA independently predicted OS for the patients with distant recurrence (P=0.007). For those patients with undetectable EBV DNA, SUVmax<8.65 was still an independent favorable prognostic factor (P=0.038).

Conclusions: SUVmax is a useful biomarker for predicting OS in nasopharyngeal carcinoma patients with locoregional recurrence or with undetectable EBV DNA. Both distant SUVmax and EBV DNA appear to be independent predictors of OS in patients with distant recurrence; however, the predictive ability of EBV DNA was superior to that of SUVmax.

Fig 1. Flowchart of patients enrolled in this study.

Fig 2. Kaplan–Meier estimates of overall survival between patients with locoregional recurrence and those with distant recurrence.

Fig 3. Kaplan–Meier estimates of overall survival according to the locoregional SUV_max or the plasma EBV DNA concentration in locoregional recurrent patients.

Fig 4. Kaplan–Meier estimates of overall survival according to the distant SUV_max or the plasma EBV DNA concentration in distant recurrent patients.