Development of a Nomogram Based on Hematological Markers and Clinical Pathological Characteristics for Predicting Cervical Lymph Node Metastasis in Oral Squamous Cell Carcinoma

Objective To investigate the value of preoperative peripheral blood markers combined with clinical pathological features in predicting cervical lymph node metastasis (CLNM) in oral squamous cell carcinoma (OSCC), and to establish and validate a nomogram prediction model. Methods A retrospective analysis was conducted on data from 239 OSCC patients who underwent surgery and pathological diagnosis at the Department of Oral Medicine, First Affiliated Hospital of Bengbu Medical College. Among them, 124 patients were included in the training set and 115 in the validation set. Patients were categorized into CLNM-positive and CLNM-negative groups based on postoperative pathological results. Preoperative predictive models for CLNM were constructed based on logistic regression analysis, and the model’s performance was validated. Results Significant differences were found between the CLNM-positive and -negative groups in gender, tumor differentiation degree, alcohol history, clinical T stage, neutrophil count, neutrophil percentage, lymphocyte count, lymphocyte percentage, C-reactive protein (CRP), neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), systemic immune inflammation index (SII), systemic inflammatory response index (SIRI), and pan-immune inflammation index (PIV) (P < 0.05). Lasso regression identified gender, lymphocyte count, platelet count, globulin, CRP, clinical T stage, and NLR as the most predictive factors. Multivariable logistic regression analysis showed that CRP, clinical T stage, and NLR were independent risk factors for CLNM in OSCC patients (P < 0.05). The nomogram prediction model was established and validated. The C-index was 0.864 (95% CI 0.802–0.927) for the training set and 0.832 (95% CI 0.746–0.919) for the validation set. Calibration curves and decision curve analysis (DCA) in both sets indicated good clinical utility of the model. Conclusions Clinical T stage, CRP, and NLR are three independent risk factors for predicting CLNM in OSCC patients. The nomogram model based on these markers shows good discriminatory ability, calibration, and clinical applicability, which can help preoperatively assess metastasis risk and improve personalized and precise treatment decisions.