Weaning protocols can improve outcomes, but their efficacy may vary with patient and staff characteristics. In this prospective, controlled trial, we compared protocol-based weaning to usual, physician-directed weaning in a closed medical intensive care unit (ICU) with high physician staffing levels and structured, system-based rounds. Adult patients requiring mechanical ventilation for more than 24 hours were assigned to usual care (UC) or protocol weaning based on their hospital identification number. Patients assigned to UC (n=145) were managed at their physicians' discretion. Patients assigned to protocol (n=154) underwent daily screening and a spontaneous breathing trial by respiratory and nursing staff without physician intervention. There were no significant baseline differences in patient characteristics between groups. The proportion of patients (protocol vs. UC) who successfully discontinued mechanical ventilation (74.7% vs. 75.2%, p=0.92), duration of mechanical ventilation (median [interquartile range]: 60.4 hours [28.6-167.0 hours] vs. 68.0 hours [27.1-169.3 hours], p=0.61), ICU (25.3% vs. 28.3%) and hospital mortality (36.4% vs. 33.1%), ICU length of stay (115 vs. 146 hours), and rates of reinstituting mechanical ventilation (10.3% vs. 9.0%) was similar. We conclude that protocol-directed weaning may be unnecessary in a closed ICU with generous physician staffing and structured rounds.