Objective To explore the prognostic value of peripheral blood neutrophil-to-lymphocyte ratio（ NLR）， platelet-to-lymphocyte ratio（ PLR）， systemic immune-inflammation index（ SII）， and systemic inflammatory response index（ SIRI） in patients with myasthenia gravis（ MG）. Methods Clinical data from 117 MG patients admitted to the Affiliated Hospital of Xuzhou Medical University between September 2018 and June 2022 were retrospectively analyzed. All patients underwent blood routine examination upon admission， with calculation of the NLR， PLR， SII and SIRI. The severity of MG was assessed using the Myasthenia Gravis Foundation of America（ MGFA） clinical classification. The Myasthenia Gravis Foundation of America-Post Intervention Status（ MGFA-PIS） was used to assess the prognosis of MG patients. Complete stable remission， pharmacological remission， and minimal manifestations were considered favorable prognoses， while states below minimal manifestations were considered poor prognoses. Patient prognosis was recorded through telephone and outpatient follow-up. Logistic regression model was employed to analyze the data， and receiver operating characteristic（ ROC） curve was used to evaluate the discriminatory efficacy of various immune markers in predicting the prognosis of MG patients. Based on the optimal cutoff values from the ROC curves of each model， samples were divided into high-expression and low-expression groups for further intergroup comparative analysis and Spearman correlation analysis. Results The favorable prognosis group（ 85 cases） and the poor prognosis group（ 32 cases） exhibited statistically significant differences in disease classification， disease duration， hematological indicators（ white blood cell count， neutrophil count， lymphocyte count）， NLR， PLR， SII， and SIRI（ P ＜ 0.05）. ROC curve analysis indicated that NLR and SIRI demonstrated good efficacy in predicting the prognosis of MG. The optimal cutoff value for NLR was 3.62， with an area under the curve（ AUC） of 0.765， specificity of 84.7%， and sensitivity of 71.9%. The optimal cutoff value for SIRI was 1.08， with an AUC of 0.754， specificity of 75.3%， and sensitivity of 71.9%. Based on optimal cutoff values（ NLR： 3.62， PLR： 128.33， SII： 962.42， SIRI： 1.08）， the results showed that the high and low NLR and SIRI groups were all statistically correlated with the duration of MG and MGFA clinical classification， the high and low SII group was startistically correlated with MGFA clinical classification（ all P＜0.05）. Spearman correlation analysis showed that SII was strongly positively correlated with prognosis（ ρ=0.555，P＜0.001）， SIRI（ ρ=0.447，P＜0.001） was moderately positively correlated with NLR（ ρ=0.386，P ＜ 0.001）， and PLR was weakly positively correlated with prognosis（ ρ=0.271，P=0.003）， with statistically significant differences. Conclusions NLR， PLR， SII， and SIRI can serve as important immune markers for prognostic evaluation of patients with MG. In particular， NLR and SIRI demonstrate strong predictive value， aiding clinicians in evaluating patients' prognostic risk and providing reference for developing personalized treatment plans.