The study investigated the association between arterial oxygen saturation (SaO2) and the incidence of cerebral infarction in patients with chronic obstructive pulmonary disease (COPD) and developed a nomogram to predict risk. It included 846 patients with COPD, including 592 in the training cohort and 254 in the internal validation cohort, data were collected from 2018 to December 2019. Predictive factors of the nomogram were systemic immune inflammatory index (SII), age, hypertension, cardiovascular disease, paraplegia and SaO2. The model achieved high predictive accuracy with an AUC of 0.85 (95% CI: 0.82–0.89) in the training cohort, 0.89 (95% CI: 0.85–0.94) in the internal validation cohort, and 0.90 (95% CI: 0.90) in the external validation on 290 patients in 2024. COPD increases the risk of cerebral infarction and the nomogram provides a useful clinical tool. The study was retrospective with a small sample of cerebral infarction subtypes and possible unmeasured influences.