Abstract
BackgroundRisk adjusted mortality for intensive care units (ICU) is usually estimated via logistic regression. Random effects (RE) or hierarchical models have been advocated to estimate provider risk-adjusted mortality on the basis that standard estimators increase false outlier classification. The utility of fixed effects (FE) estimators (separate ICU-specific intercepts) has not been fully explored.MethodsUsing a cohort from the Australian and New Zealand Intensive Care Society Adult Patient Database, 2009–2010, the model fit of different logistic estimators (FE, random-intercept and random-coefficient) was characterised: Bayesian Information Criterion (BIC; lower values better), receiver-operator characteristic curve area (AUC) and Hosmer-Lemeshow (H-L) statistic. ICU standardised hospital mortality ratios (SMR) and 95%CI were compared between models. ICU site performance (FE), relative to the grand observation-weighted mean (GO-WM) on odds ratio (OR), risk ratio (RR) and probability scales were assessed using model-based average marginal effects (AME).ResultsThe data set consisted of 145355 patients in 128 ICUs, years 2009 (47.5%) & 2010 (52.5%), with mean(SD) age 60.9(18.8) years, 56% male and ICU and hospital mortalities of 7.0% and 10.9% respectively. The FE model had a BIC = 64058, AUC = 0.90 and an H-L statistic P-value = 0.22. The best-fitting random-intercept model had a BIC = 64457, AUC = 0.90 and H-L statistic P-value = 0.32 and random-coefficient model, BIC = 64556, AUC = 0.90 and H-L statistic P-value = 0.28. Across ICUs and over years no outliers (SMR 95% CI excluding null-value = 1) were identified and no model difference in SMR spread or 95%CI span was demonstrated. Using AME (OR and RR scale), ICU site-specific estimates diverged from the GO-WM, and the effect spread decreased over calendar years. On the probability scale, a majority of ICUs demonstrated calendar year decrease, but in the for-profit sector, this trend was reversed.ConclusionsThe FE estimator had model advantage compared with conventional RE models. Using AME, between and over-year ICU site-effects were easily characterised.
Highlights
Risk-adjusted mortality has been used to characterise the performance of health care providers for a number of years [1] and has generated a substantial [2] if not controversial [3] literature
Records were used only when all three components of the Glasgow Coma Score (GCS) were provided; records for which all physiologic variables were missing were excluded, and for the remaining records, missing variables were replaced with the normal range and weighted [32]
The data set consisted of 145355 patient records in 128 intensive care units (ICU), calendar years 2009 (47.5%) & 2010 (52.5%), with mean(SD) age
Summary
Risk-adjusted mortality has been used to characterise the performance of health care providers for a number of years [1] and has generated a substantial [2] if not controversial [3] literature. Mortality probability estimation usually proceeds via conventional logistic regression [8] but a call for ‘‘Improving the statistical approach to health care provider profiling’’, in particular the use of Bayesian methods, was made some 15 years ago [9]. Advances in standard statistical software packages have made such approaches feasible and a random effects or hierarchical approach to estimation, both Bayesian and frequentist, has recently been advocated [10,11] and implemented [12] Such recommendation must address certain cautions recently advanced regarding the latter methods [13,14], in particular the reduction of variation of hospital performance by the shrinkage effect of conventional random effects models. The utility of fixed effects (FE) estimators (separate ICU-specific intercepts) has not been fully explored
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
