Design of a Predictive Recurrence Scoring System in Oral Squamous Cell Carcinoma

Introduction: Oral squamous cell carcinoma (OSCC) is a frequent head and neck malignancy with high morbidity and mortality. Locoregional recurrence is the main determinant of long-term prognosis, yet reliable predictive models remain limited. This study aimed to identify clinicopathological predictors of recurrence and to develop a nomogram-based recurrence risk score (RRS) for patient stratification. Materials and Methods: A retrospective study was conducted including 332 patients with histologically confirmed OSCC treated surgically between 2012 and 2022. Clinical and pathological variables were analyzed. Statistical analyses included Chi-squared tests, Cox regression, Kaplan-Meier survival analysis, and multivariate modeling to construct a predictive nomogram and derive the RRS. Results: Close or involved surgical margins were observed in 33.4% of patients, and 66.9% presented moderately or poorly differentiated tumors. Locoregional recurrence occurred in 34.6% of cases, mainly within 24 months. Close margins and poor differentiation were independent predictors of recurrence (p < 0.005). The RRS effectively stratified patients into low-, intermediate-, and high-risk groups, with recurrence rates of 21.6%, 50.6%, and 82.1%, respectively (p < 0.001). Conclusions: The RRS is a practical tool for predicting OSCC recurrence and may support personalized follow-up and adjuvant treatment strategies. Prospective validation is warranted.