Traumatic brain injury (TBI) is a leading cause of morbidity and mortality in trauma patients, necessitating reliable prognostic tools. The segmented neutrophil-to-monocyte (SeMo) ratio, indicative of the inflammatory response, has emerged as a valuable biomarker. This study evaluates the prognostic value of dynamic changes in the SeMo ratio in predicting outcomes for patients with moderate to severe TBI. A retrospective analysis was conducted on data from 1118 TBI patients admitted to the surgical intensive care unit at a level I trauma center between January 2009 and December 2020. Patients were selected based on an Abbreviated Injury Scale (AIS) score ≥ 3 in the head region. Initial and follow-up SeMo ratios were calculated upon admission and 48-72 h later, respectively. The dynamic SeMo ratio was defined as the difference between the second and initial SeMo ratios. Statistical analyses included receiver operating characteristic (ROC) curve analysis to determine the optimal threshold for mortality prediction, and comparative analysis of clinical outcomes. The study cohort included 121 deceased and 997 surviving patients. Deceased patients had significantly higher second SeMo ratios (20.9 ± 16.1 vs. 15.8 ± 17.2, p = 0.001) and dynamic SeMo ratios (2.4 ± 19.8 vs. -2.1 ± 19.5, p = 0.019) than those survival patients. In the multivariate analysis, the dynamic SeMo is a significant independent risk factor for in-hospital mortality (OR 1.01, 95%CI: 1.01-1.03, p = 0.031). The optimal cut-off for the dynamic SeMo ratio was 5.96, above which patients exhibited higher mortality (21.4% vs. 8.5%, p < 0.001), higher adjusted mortality (adjusted odds ratio: 2.98; 95% confidence interval: 1.95-4.56; p = 0.005), and longer hospital stays (23.6 days vs. 19.7 days, p = 0.005). Dynamic SeMo ratio changes serve as a prognostic marker for in-hospital mortality and hospital stay duration in moderate to severe TBI patients. A higher dynamic SeMo ratio indicates increased risk, highlighting the importance of early monitoring and intervention. Future prospective studies should validate these findings and explore integration with other biomarkers for enhanced prognostication.