Key result
Treating in-hospital mortality as a competing risk provides valid estimates for length of hospital stay and time to clinical stability, whereas ad-hoc approaches yield disparate and conceptually problematic results.
Population
1,635 patients aged ≥65 years admitted to the hospital with Community Acquired Pneumonia from the…
Design
Other
Follow-up
30 days
Authors
Loading...
Supports competing-risk models for valid length-of-stay estimates in cohorts; leaves open whether ad-hoc methods alter clinical inferences.
When analyzing time-to-event outcomes like length of stay where in-hospital mortality prevents the event, mortality should be treated as a competing risk rather than handled with ad-hoc censoring methods.
Brock et al. (2011) studied Community Acquired Pneumonia (n=1,635). Competing risks analysis vs. Ad-hoc survival analysis methods (e.g., Kaplan-Meier, restricted analysis) was evaluated on Probability of hospital discharge and clinical stability. Treating in-hospital mortality as a competing risk provides valid estimates for length of hospital stay and time to clinical stability, whereas ad-hoc approaches yield disparate and conceptually problematic results.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: