Prognostic Model for Stratification of Radioresistant Nasopharynx Carcinoma to Curative Salvage Radiotherapy

Purpose To investigate for a prognostic index (PI) to personalize recommendations for salvage intensity-modulated radiotherapy (IMRT) in patients with locally recurrent nasopharyngeal carcinoma (lrNPC). Methods Patients with lrNPC from two academic institutions (Sun Yat-Sen University Cancer Center [SYSUCC-A; n = 251 (training cohort)] and National Cancer Centre Singapore [NCCS; n = 114] and SYSUCC-B [n = 193 (validation cohorts)]) underwent salvage treatment with IMRT from 2001 to 2015. Primary and secondary clinical end points were overall survival (OS) and grade 5 toxicity-free rate (G5-TFR), respectively. Covariate inclusion to the PIs was qualified by a multivariable two-sided P < .05. Discrimination and calibration of the PIs were assessed. Results The primary PI comprised covariates that were adversely associated with OS in the training cohort (gross tumor volume recurrence hazard ratio [HR], 1.01/mL increase [ P < .001], age recurrence HR, 1.02/year increase [ P = .008]; repeat IMRT equivalent dose in 2-Gy fractions [EQD2] ≥ 68 Gy HR, 1.42 [ P = .03]; prior radiotherapy-induced grade ≥ 3 toxicities HR, 1.90 [ P = .001]; recurrent tumor [rT]-category 3 to 4 HR, 1.96 [ P = .005]), in ascending order of weight. Discrimination of the PI for OS was comparable between training and both validation cohorts (Harrell’s C = 0.71 [SYSUCC-A], 0.72 [NCCS], and 0.69 [SYSUCC-B]); discretization by using a fixed PI score cutoff of 252 determined from the training data set yielded low- and high-risk subgroups with disparate OS in the validation cohorts (NCCS HR, 3.09 [95% CI, 1.95 to 4.89]; SYSUCC-B HR, 3.80 [95% CI, 2.55 to 5.66]). Our five-factor PI predicted OS and G5-TFR (predicted v observed 36-month OS and G5-TFR, 22% v 15% and 38% v 44% for high-risk NCCS and 26% v 31% and 45% v 46% for high-risk SYSUCC-B). Conclusion We present a validated PI for robust clinical stratification of radioresistant NPC. Low-risk patients represent ideal candidates for curative repeat IMRT, whereas novel clinical trials are needed in the unfavorable high-risk subgroup.