Despite careful evaluation of changes in hospital care for community-acquired pneumonia (CAP), little is known about intensive care unit (ICU) use in the treatment of this disease. There are criteria that define CAP as "severe," but evaluation of their predictive value is limited. We compared characteristics, course, and outcome of inpatients who did (n = 170) and did not (n = 1,169) receive ICU care in the Pneumonia Patient Outcomes Research Team prospective cohort. We also assessed the predictive characteristics of four prediction rules (the original and revised American Thoracic Society criteria, the British Thoracic Society criteria, and the Pneumonia Severity Index [PSI]) for ICU admission, mechanical ventilation, medical complications, and death (as proxies for severe CAP). ICU patients were more likely to be admitted from home and had more comorbid conditions. Reasons for ICU admission included respiratory failure (57%), hemodynamic monitoring (32%), and shock (16%). ICU patients incurred longer hospital stays (23.2 vs. 9.1 days, p < 0.001), higher hospital costs (21,144 dollars vs. 5,785 dollars, p < 0.001), more nonpulmonary organ dysfunction, and higher hospital mortality (18.2 vs. 5.0%, p < 0.001). Although ICU patients were sicker, 27% were of low risk (PSI Risk Classes I-III). Severity-adjusted ICU admission rates varied across institutions, but mechanical ventilation rates did not. The revised American Thoracic Society criteria rule was the best discriminator of ICU admission and mechanical ventilation (area under the receiver operating characteristic curve, 0.68 and 0.74, respectively) but none of the prediction rules were particularly good. The PSI was the best predictor of medical complications and death (area under the receiver operating characteristic curve, 0.65 and 0.75, respectively), but again, none of the prediction rules were particularly good. In conclusion, ICU use for CAP is common and expensive but admission rates are variable. Clinical prediction rules for severe CAP do not appear adequately robust to guide clinical care at the current time.