Abstract Objective: Neurosyphilis is challenging to diagnose, especially in patients with human immunodeficiency virus (HIV)/syphilis co-infection. The aim of this study was to profile the clinical features of neurosyphilis and evaluate the correlation between neurosyphilis and clinical or laboratory factors among patients with HIV/syphilis co-infection. Methods: We retrospectively analyzed the data of 479 HIV/syphilis co-infected patients examined between August 2009 and September 2018. A multivariate logistic regression model was used to identify factors correlated with neurosyphilis. Results: The overall prevalence of neurosyphilis was 21.7%. The prevalence of neurosyphilis differed among patients with primary (11.1%), secondary (20.1%), and latent syphilis (29.1%). The prevalences of neurosyphilis in patients with serological non-response and serofast patients were 26.1% and 6.3%, respectively, while 12.5% of patients with serological relapse had neurosyphilis. Patients with secondary and latent syphilis had serum rapid plasma reagin (RPR) titers (per unit) of 1.44-fold [95% confidence interval (CI): 1.08–1.93, P = 0.014] and 2.73-fold (95% CI: 1.49–5.00, P = 0.001), respectively, which increased the risk of confirmed neurosyphilis. Among patients with latent syphilis, a serum RPR titer of ≥1:32 and peripheral blood CD4 cell count of ≤350/mL were significantly associated with neurosyphilis, with adjusted odds ratios of 9.45 (95% CI: 1.86–48.03, P = 0.007) and 3.75 (95% CI: 1.11–12.66, P = 0.033), respectively. Conclusion: A serum RPR titer of ≥1:32 and a peripheral blood CD4 cell count of ≤350/mL have predictive value in screening for neurosyphilis among HIV-positive patients with latent syphilis.