The study aimed to develop a predictive model to identify the risk of pulmonary infection in patients with cerebral hemorrhage, as these infections significantly affect recovery and survival rates. The research included 350 hospitalized patients with a diagnosis of brain hemorrhage, of whom 49.1% developed a lung infection. Elevated levels of C-reactive protein (CRP), prolonged stay in the intensive care unit (ICU) and lower frequency of oral care were identified as significant risk factors. The final predictive model included four key variables: proton pump inhibitor use, CRP levels, frequency of oral care, and ICU length of stay, achieving high accuracy with an area under the curve (AUC) of 0.938. The results suggest that this model allows doctors to more accurately identify patients at high risk of lung infection. Integrating the model into clinical practice together with targeted nursing interventions may reduce the incidence of pulmonary infections and improve the overall prognosis of patients with cerebral hemorrhage.