Effect of diagnosis related groups implementation on the intensive care unit of a Swiss tertiary hospital: a cohort study

Abstract

Background: In 2013 the Swiss Diagnosis Related Groups ((Swiss)-DRG) was implemented in Intensive Care Units (ICU). Its impact on hospitalizations has not yet been examined. We compared the number of ICU admissions, according to clinical severity and referring institution, and screened whether implementation of Swiss-DRG affected admission policy, ICU length-of-stay (ICU-LOS) or ICU mortality.

Methods: Retrospective, single centre, cohort study conducted at the University Hospital Zurich, Switzerland between January 2009 and end of September 2013. Demographic and clinical data was retrieved from a quality assurance database.

Results: Admissions (n = 17,231) before the introduction of Swiss-DRG were used to model expected admissions after DRG, and then compared to the observed admissions. Forecasting matched observations in patients with a high clinical severity admitted from internal units and external hospitals (admitted / predicted: 709 / 703, [95% Confidence Interval (CI), 658-748] and 302 / 332, [95% CI, 269-365] respectively). In patients with low severity of disease, in-house admissions became more frequent than expected and external admission were less frequent (admitted / predicted: 1972 / 1910, [95% CI, 1898-1940] and 436 / 518, [95% CI, 482-554] respectively). Various mechanisms related to Swiss-DRG may have led to these changes. DRG could not be linked to significant changes in regard to ICU-LOS and ICU mortality.

Conclusions: DRG introduction had not affected ICU admissions policy, except for an increase of in-house patients with a low clinical severity of disease. DRG had neither affected ICU mortality nor ICU-LOS.

Keywords: DRG; Diagnosis related groups; Epidemiology; ICU admissions; Switzerland.

Fig. 1

DRG affected admissions of patient with a low burden of disease. Patients were stratified by the year of admission, the origin of admission (in-house (a, b); from external hospitals (c, d)) and clinical severity at admission (SAPS II score < 40 (a, c); SAPS ≥40 (b, d)). Observed admissions in 2013 (x) are considered significantly affected by DRG if outside the 95% CI (whisker) of predicted admissions for 2013 (-) based admissions observed 2009 to 2012 (•). Forecasted and observed admissions were 1919 (95% CI: 1898–1940) and 1972 in (a), 703 (95% CI: 658–748) and 709 in (b), 518 (95% CI: 482–554) and 436 in (c) and 332 (95% CI: 269–395) and 302 respectively in (d)

Fig. 2

Relation between the clinical severity of disease at admission (SAPS II) and the ICU LOS. a Evolution of ICU LOS between 2009 and 2013. Comparison between the years (One-Way ANOVA) and to 2013 (Dunnett t-tests) n.s. b ICU LOS stratified by SAPS II and year of admission. ICU LOS in survivors (c) and no survivors (d) stratified by the year of admission and the clinical severity at admission (SAPS II Score)

Fig. 3

DRG did not increase the ICU mortality. a Intensive care unit mortality according to the year of admission and stratified by the clinical severity at admission (SAPS II score). b Mean residuals of Chi-square test assessing independency of ICU mortality and years 2009 to 2013, stratified by the clinical severity at admission (SAPS II score); asterisk refers to significant mortality difference with the other years. P < 0.5 (*), < 0.01 (**) < 0.001 (***)