Previous studies have confirmed that patients with obstructive sleep apnea (OSA) have higher systemic inflammatory markers, including intercellular adhesion molecule-1(ICAM-1), vascular cell adhesion molecule-1(VCAM-1), and E-selectin compared to control subjects. However, the effects of continuous positive airway pressure (CPAP) therapy on circulating levels of ICAM-1, VCAM-1, and E-selectin in OSA patients remain inconsistent. Therefore, the primary purpose of the present meta-analysis is to estimate the effect of CPAP therapy on these cell adhesion molecules (CAMs) in patients with OSA. The PubMed, Scopus, Embase, and Cochrane Library databases were searched. The overall effects were measured by the standardized mean difference (SMD) with a 95% confidence interval (CI). A random effects model or a fixed-effects model was used, depending on the heterogeneity of the studies. A total of 11 studies were included, comprising 650 OSA patients. The pooled results showed that CPAP therapy significantly decreased ICAM-1 (SMD = - 0.283, 95% CI - 0.464 to - 0.101, p = 0.002) and E-selectin levels (SMD = - 0.349, 95% CI - 0.566 to - 0.133, p = 0.002). In contrast, there was no significant improvement of VCAM-1 levels after CPAP treatment (SMD = - 0.160, 95% CI - 0.641 to 0.320, p = 0.513). Our meta-analysis demonstrated that CPAP treatment significantly decreased the circulating levels of ICAM-1 and E-selectin in OSA patients. Thus, ICAM-1 and E-selectin may be effective markers to evaluate CPAP therapy for reducing OSA cardiovascular risk in clinical practice.