Molecular predictors of locoregional and distant metastases in oropharyngeal squamous cell carcinoma

Background: The incidence of oropharyngeal squamous cell carcinoma (OPSCC) is increasing due to fundamental changes in oncogenesis related to effects of the human papilomavirus (HPV). Virally-mediated tumours behave and respond to treatment differently than their classic, carcinogenically-mediated counterparts despite similar stage and grade of disease. This difference in behaviour has lead to investigation of etiologies of OPSCC at the molecular level. Molecular biomarkers offer potential insight into the behaviour of OPSCC. Identifying a subset of patients that are more likely to have recurrence and distant metastasis is valuable for prognostication and treatment planning. There is limited information regarding the profiles of these biomarkers in locoregional and distant metastases in OPSCC. Objective: This study was designed to identify biomarker profiles predictive of locoregional and distant metastases and recurrence in OPSCC. Methods: Cross-sectional study of a prospectively-collected oropharyngeal tumour database was undertaken. All patients with OPSCC presenting to the University of Alberta Hospital from 2002-2009 were included in the study. Data collection from the Alberta Cancer Registry, including demographics, nodal status, distant metastases, treatment, recurrence, and survival, was undertaken. Tissue micro-arrays (TMAs) were constructed for each tumour specimen using triplicate cores (0.6mm) of formalin-fixed, paraffin-embedded (FFPE) pre-treatment tumour tissue. TMAs were processed using immunohistochemistry for p16, EGFR, Ki67, p53, and Bcl-XL. Positivity for each biomarker was determined using quantified AQUAnalysis r scores on histoplots. Multivariate statistics were utilized to assess the relationship between each biomarker and locoregional and distant metastases, as well as recurrence-free survival (RFS). Results: High expression of p16 (p= 0.000) and Bcl-XL (p= 0.039) independently demonstrated a significant association with nodal disease at presentation. Kaplan-Meier analysis demonstrated improved RFS in patients with high p16 and decreased RFS in patients with high p53 expression. Cox regression analysis supported p16 as an independent prognosticator for improved RFS. p53 demonstrated an association with recurrence, but when compared to p16 status, nodal status, and staging, was not an independent predictor of recurrence. Conclusions: Biomarker profiling using p16, Bcl-xL, and p53 may be useful in prognostication and treatment planning in patients with OPSCC.