Objective To analyze the value of serum myeloid-related proteins 8/14 (MRP8/14) and Krüppel-like factor 2 (KLF2) levels in predicting prognosis for patients with acute respiratory distress syndrome (ARDS).Methods A total of 148 patients with ARDS admitted to Xinjiang Uygur Autonomous Region People's Hospital from June 2022 to June 2025 were selected. Follow-up was conducted for 28 days, and the patients were divided into the death group (n = 57) and the survival group (n = 91). The serum levels of MRP8/14 and KLF2 and clinical data were compared between the groups, and the influencing factors for the prognosis of ARDS patients and the predictive value of serum MRP8/14 and KLF2 levels for the death of ARDS patients were analyzed.Results The serum MRP8/14 levels in the death group were higher than those in the survival group (P < 0.05), and the serum KLF2 levels in the death group were lower than those in the survival group (P < 0.05). The death group had older age, and higher Sequential Organ Failure Assessment (SOFA) scores and Acute Physiology And Chronic Health Evaluation Ⅱ (APACHE Ⅱ) scores at admission compared to the survival group (P < 0.05). The multivariable regression analysis revealed that high serum MRP8/14 levels [O^R = 3.364 (95% CI: 1.582, 7.154) ], high SOFA scores at admission [O^R = 3.770 (95% CI: 1.645, 8.638) ], and high APACHE Ⅱ scores at admission [O^R = 4.112 (95% CI: 1.568, 10.786) ] were risk factors for death in ARDS patients (P < 0.05), while high serum KLF2 levels [O^R = 0.361 (95% CI: 0.196, 0.665) ] were a protective factor for death in ARDS patients (P < 0.05). The receiver operating characteristic (ROC) curve analysis demonstrated that the area under the curve of the combination of serum MRP8/14 and KLF2 levels for predicting death in ARDS patients was 0.905, with a sensitivity of 89.47% (95% CI: 0.778, 0.956) and a specificity of 93.41% (95% CI: 0.857, 0.973).Conclusion Serum MRP8/14 and KLF2 levels are closely related to the 28-day mortality of ARDS patients, and the combined detection of these two indicators can improve the predictive performance for the prognosis of ARDS patients.