Objective: To study the correlation between serum microRNA (miR)-491-5p and gap junction alpha-1 (GJA1) levels and cognitive impairment in patients with acute cerebral infarction (ACI). Methods: 139 patients with ACI were collected as the research subjects, and they were separated into normal cognitive group (n=68) and cognitive impairment group (n=71). ELISA was applied to detect serum GJA1 level, RT-PCR was applied to detect miR-491-5p level, Logistic regression was applied to analyze the influencing factors of cognitive impairment in patients with ACI. ROC curve was applied to analyze the diagnostic value of serum miR-491-5p and GJA1 levels for cognitive impairment in patients with ACI. Results: Compared with the cerebral infarction cognitive normal group, the serum miR-491-5p and GJA1 levels in the cerebral infarction cognitive impairment group were reduced (P<0.05). Statistically significant differences between the cognitively impaired group and the cognitively normal group were found between age, area of cerebral infarction, NIHSS score, and history of hypertension (P<0.05). Age, area of cerebral infarction, NIHSS score, and history of hypertension were risk factors affecting patients with ACI combined with cognitive impairment (P<0.05), and elevated levels of miR-491-5p and GJA1 were protective factors (P<0.05). Drawing receiver operating characteristic, it was found that the AUC of serum miR-491-5p, GJA1 levels and their combination in diagnosis of cognitive dysfunction in patients with ACI was 0.842, 0.857 and 0.931, respectively, the combined diagnosis was obviously better than that of miR-491-5p and GJA1 separately. Conclusion: Reduced levels of miR-491-5p and GJA1 in patients with ACI cognitive impairment have a certain auxiliary diagnostic value for ACI-complicated cognitive dysfunction, and the combined auxiliary diagnostic value is higher.