Effects on patients of their healthcare practitioner's or institution's participation in clinical trials: a systematic review

Background: Systematic reviews have shown uncertainty about the size or direction of any 'trial effect' for patients in trials compared to those treated outside trials. We are not aware of any systematic review of whether there is a 'trial effect' related to being treated by healthcare practitioners or institutions that take part in research. Methods: We searched the Cochrane Methodology Register and MEDLINE (most recently in January 2009) for studies in which patients were allocated to treatment in one or other setting, and cohort studies reporting the outcomes of patients from different settings. We independently assessed study quality, including the control of bias in the generation of the comparison groups, and extracted data. Results: We retrieved and checked more than 15,000 records. Thirteen articles were eligible: five practitioner studies and eight institution studies. Meta-analyses were not possible because of heterogeneity. Two practitioner studies were judged to be 'controlled' or better. A Canadian study among nurses found that use of research evidence was higher for those who took part in research working groups and a Danish study on general practitioners found that trial doctors were more likely to prescribe in accordance with research evidence and guidelines. Five institution studies were 'controlled' but provided mixed results. A study of North American patients at hospitals that had taken part in trials for myocardial infarction found no statistically significant difference in treatment for patients in trial and non-trial hospitals. A Canadian study of myocardial infarction patients found that trial participants had better survival than patients in the same hospitals who were not in trials or those in non-trial hospitals. A study of general practices in Denmark did not detect differences in guideline adherence between trial and non-trial practices but found that trial practices were more likely to prescribe the trial sponsor's drugs. The other two 'controlled' studies of institutions found lower mortality in trial than non-trial hospitals. Conclusions: The available findings from existing research suggest that there might be a 'trial effect' of better outcomes, greater adherence to guidelines and more use of evidence by practitioners and institutions that take part in trials. However, the consequences for patient health are uncertain and the most robust conclusion may be that there is no apparent evidence that patients treated by practitioners or in institutions that take part in trials do worse than those treated elsewhere.