A clinically integrated post-graduate training programme in evidence-based medicine versus 'no intervention' for improving disability evaluations: a cluster randomised clinical trial

Abstract

Background: Although several studies have shown that teaching EBM is effective in improving knowledge, at present, there is no convincing evidence that teaching EBM also changes professional behaviour in practice. Therefore, the primary aim of this study was to evaluate the effectiveness of a clinically integrated post-graduate training programme in EBM on evidence-based disability evaluation.

Methods and findings: In a cluster randomised controlled trial, fifty-four case-based learning groups consisting of 132 physicians and 1680 patients were randomly assigned to the intervention or control groups. A clinically integrated, post-graduate, 5-day training programme in evidence-based medicine, consisting of (home) assignments, peer teaching, interactive training in searching databases, lectures and brainstorming sessions was provided to the intervention group. The control group received no training. The primary outcome was evidence-based disability evaluation, as indicated by the frequency in use of evidence of sufficient quality in disability evaluation reports. There are no general EBM behaviour outcome measures available. Therefore, we followed general guidelines for constructing performance indicators and defined an a priori cut-off for determination of sufficient quality as recommended for evaluating EB training. Physicians trained in EBM performed more evidence-based disability evaluations compared to physicians in the control group (difference in absolute proportion 9.7%, 95% CI 3.5 to 15.9). The primary outcome differences between groups remained significant after both cluster-adjusted analysis and additional sensitivity analyses accounting for subjects lost to follow-up.

Conclusions: A EBM programme successfully improved the use of evidence in a non-hospital based medical specialty. Our findings support the general recommendations to use multiple educational methods to change physician behaviour. In addition, it appeared important that the professional context of the intervention was very supportive in the sense that searches in databases, using and applying guidelines and other forms of evidence are considered standard practice and are encouraged by colleagues and management.

Figure 1. Flow of clusters (c) and physicians (n) through the trial for primary outcome analysis.