Did a quality improvement collaborative make stroke care better? A cluster randomized trial

Abstract

Background: Stroke can result in death and long-term disability. Fast and high-quality care can reduce the impact of stroke, but UK national audit data has demonstrated variability in compliance with recommended processes of care. Though quality improvement collaboratives (QICs) are widely used, whether a QIC could improve reliability of stroke care was unknown.

Methods: Twenty-four NHS hospitals in the Northwest of England were randomly allocated to participate either in Stroke 90:10, a QIC based on the Breakthrough Series (BTS) model, or to a control group giving normal care. The QIC focused on nine processes of quality care for stroke already used in the national stroke audit. The nine processes were grouped into two distinct care bundles: one relating to early hours care and one relating to rehabilitation following stroke. Using an interrupted time series design and difference-in-difference analysis, we aimed to determine whether hospitals participating in the QIC improved more than the control group on bundle compliance.

Results: Data were available from nine interventions (3,533 patients) and nine control hospitals (3,059 patients). Hospitals in the QIC showed a modest improvement from baseline in the odds of average compliance equivalent to a relative improvement of 10.9% (95% CI 1.3%, 20.6%) in the Early Hours Bundle and 11.2% (95% CI 1.4%, 21.5%) in the Rehabilitation Bundle. Secondary analysis suggested that some specific processes were more sensitive to an intervention effect.

Conclusions: Some aspects of stroke care improved during the QIC, but the effects of the QIC were modest and further improvement is needed. The extent to which a BTS QIC can improve quality of stroke care remains uncertain. Some aspects of care may respond better to collaboratives than others.

Trial registration: ISRCTN13893902.

Figure 1

Bundle compliance. In this example only patient 3 would be classed as receiving care that was bundle compliant.

Figure 2

Flow diagram of participation.

Figure 3

Bundle compliance over time in the control and intervention group. In bundle 1, for the control group, compliance went from 24.3% to 37.5% (13.2% change) and in the intervention group, from 19.6% to 42.3% (22.7% change). On crude comparison, this is a difference of 9.5%, but with all the various adjustments for clustering, this results in a relative benefit of 10.9% in the intervention relative to the control group.