Addressing Competing Risks When Assessing the Impact of Health Services Interventions on Hospital Length of Stay

Background: Although hospital length of stay is generally modeled continuously, it is increasingly recommended that length of stay should be considered a time-to-event outcome (i.e., time to discharge). Additionally, in-hospital mortality is a competing risk that makes it impossible for a patient to be discharged alive. We estimated the effect of trauma center accreditation on risk of being discharged alive while considering in-hospital mortality as a competing risk. We also compared these results with those from the naive approach, with length of stay modeled continuously. Methods: Data include admissions to a level I trauma center in Quebec, Canada, between 2008 and 2017. We computed standardized risk of being discharged alive at specific days by combining inverse probability weighting and the Aalen-Johansen estimator of the cumulative incidence function. We estimated effect of accreditation using pre-post, interrupted time series (ITS) analyses, and the naive approach. Results: Among 5,300 admissions, 12% died, and 83% were discharged alive within 60 days. Following accreditation, we observed increases in risk of discharge between the 7th day (4.5% [95% CI = 2.3, 6.6]) and 30th day since admission 3.8% (95% CI = 1.5, 6.2). We also observed a stable decrease in hospital mortality, -1.9% (95% CI = -3.6, -0.11) at the 14th day. Although pre-post and ITS produced similar results, we observed contradictory associations with the naive approach. Conclusions: Treating length of stay as time to discharge allows for estimation of risk of being discharged alive at specific days after admission while accounting for competing risk of death.

Automated summary

This study found that accreditation of a level I trauma center was associated with increased risk of being discharged alive at specific days after admission, along with a stable decrease in hospital mortality. The results from pre-post and interrupted time series analyses were consistent, contrasting with contradictory associations observed with the naive approach.