Objective: To investigate the effect of dexmedetomidine (DEX) on the incidence of delirium and clinical prognosis in patients with neurosurgical ICU. Methods: This study was a retrospective cohort study that enrolled patients admitted to the Neurosurgery ICU of our hospital between January 2021 and December 2023 who required mechanical ventilation (duration > 48 hours). Based on sedation protocols, patients were divided into a dexmedetomidine group (DEX group, n = 60) and a midazolam routine sedation group (control group, n = 60). The primary endpoint was the incidence of delirium during ICU stay, while secondary endpoints included mechanical ventilation duration, ICU length of stay, 28-day mortality rate, and adverse events. Results: The incidence of delirium in the DEX group was significantly lower than that in the control group (31.7% vs. 58.3%, p = 0.004). Additionally, the duration of mechanical ventilation in the DEX group was significantly shorter than that in the control group [(7.2 ± 2.5) days vs. (9.8 ± 3.4) days, p < 0.001], and the ICU stay was also significantly reduced [(13.5 ± 4.2) days vs. (16.8 ± 5.7) days, p = 0.002]. There were no statistically significant differences in the 28-day mortality rate (DEX group: 13.3% vs. control group: 16.7%, p = 0.59) or the rate of unintended extubation (DEX group: 3.3% vs. control group: 5.0%, p = 0.64) between the two groups. In terms of safety, the incidence of bradycardia was significantly higher in the DEX group than in the control group (15.0% vs. 3.3%, p = 0.03). Conclusion: In neurosurgical patients on mechanical ventilation, dexmedetomidine sedation can effectively reduce the incidence of delirium and shorten the duration of mechanical ventilation and ICU stay, but the potential risk of bradycardia should be monitored.