Background <p>Obstructive sleep apnea (OSA) is a common disorder closely associated with inflammation, yet the relationship between certain inflammatory biomarkers and cardiovascular mortality in OSA patients remains unclear. This study compared the predictive value of different inflammatory biomarkers for prognosis in probable obstructive sleep apnea (pOSA) patients and examined the mediating role of hematocrit (HCT) in the association between monocyte-to-lymphocyte ratio (MLR) and cardiovascular mortality.</p> Methods <p>Based on data from the U.S. National Health and Nutrition Examination Survey (NHANES, 2005–2008 and 2015–2018), 6,844 pOSA patients were identified. The predictive efficacy of seven inflammatory biomarkers for 1-year cardiovascular mortality was assessed using receiver operating characteristic (ROC) curves, identifying MLR as the optimal predictor. We analyzed the 1-, 3-, and 5-year ROC curves for MLR. X-tile software determined the optimal cutoff value for MLR and grouped patients accordingly. Weighted multivariable Cox proportional hazards models, Kaplan–Meier curves, and restricted cubic spline (RCS) analyses examined the relationship between MLR and cardiovascular mortality in pOSA patients. Subgroup analyses were conducted in the fully adjusted model. Sensitivity analyses were performed to verify the robustness of the results. Statistical mediation analysis was conducted to explore the mediating role of HCT.</p> Results <p>MLR demonstrated the highest area under the curve (AUC) for predicting 1-year cardiovascular mortality in pOSA patients (AUC = 0.811). Its predictive performance gradually declined as the follow-up period lengthened. Weighted multivariable Cox analysis revealed MLR as an independent predictor of cardiovascular death (HR = 5.08, 95% CI 2.72–9.50, <i>p</i> &lt; 0.001). Survival analysis revealed the lowest survival rate in the high-MLR group (<i>p</i> &lt; 0.001). RCS indicated a nonlinear positive correlation between MLR and cardiovascular mortality risk (nonlinear <i>p</i> &lt; 0.05). The results of sensitivity analyses were consistent with the main analysis. Statistical mediation analysis showed that HCT played a partial mediating role, with a mediation effect size of 0.002 (<i>p</i> = 0.004).</p> Conclusions <p>MLR is independently associated with cardiovascular mortality in patients with pOSA, and HCT potentially mediates part of this association. MLR may serve as a supplementary tool for cardiovascular risk stratification and prognosis assessment in pOSA patients.</p> Graphical Abstract <p>Proposed pathways linking intermittent hypoxia, inflammation, hemorheological changes, and cardiovascular mortality in pOSA patients. <i>NHANES</i> National Health and Nutrition Examination Survey, <i>OSA</i> obstructive sleep apnea, <i>pOSA</i> probable obstructive sleep apnea, <i>MLR</i> monocyte-to-lymphocyte ratio, <i>HCT</i> hematocrit, <i>HR</i> hazard ratio, <i>AUC</i> area under the curve</p> <p></p>