Propensity score adjustment for pretreatment differences between hospitalized and ambulatory patients with community-acquired pneumonia. Pneumonia Patient Outcomes Research Team (PORT) Investigators.

Author(s): Obrosky, D., Singer, D., Kapoor, W., Fine, M.

Journal/Book: Medical Care. 1995; 33(4 Suppl): AS56-66.

Abstract: A primary goal of the Pneumonia Patient Outcomes Research Team (PORT) multicenter cohort study is to identify a subgroup of patients with community-acquired pneumonia (CAP) who could be safely treated on an ambulatory basis. The medical outcomes of inpatients and outpatients are to be compared. Propensity score adjustment provides a unified way to control for pretreatment differences in the analysis of all the outcomes in this nonrandomized study by defining "comparable" patients as those with the same propensity score (i.e., the same probability of hospitalization). Data for 747 patients (35.5% hospitalized) with CAP in the Pneumonia PORT study illustrate the development and assessment of a propensity score adjustment. A classification tree algorithm defined seven propensity score strata with hospitalization probabilities ranging from 6.5% to 76.5%. Statistically significant pretreatment imbalances favoring the outpatients were found for 29 of 44 baseline variables considered; after stratification on the propensity score, only 13 of the 29 imbalances remained statistically significant at the 0.05 level. Post hoc stratification on the estimated propensity score consistently reduced, but did not completely eliminate, systematic baseline differences between ambulatory and hospitalized patients with CAP. Regression adjustment can be used in conjunction with propensity score stratification to adjust further for the remaining identified imbalances.

Keyword(s): causal inference in nonrandomized studies

Zurück | Weiter