Leveraging published randomized controlled trials to inform clinical trial design: a simulation-based study of laminectomy versus laminectomy and fusion.

Abstract

The US-based Spinal Laminectomy versus Instrumented Pedicle Screw (SLIP) trial reported improvement in disability following laminectomy with fusion versus laminectomy alone for patients with lumbar spondylolisthesis. Despite using similar methods, a concurrent Swedish trial investigating the same question did not reach the same conclusion. The authors performed a simulation-based analysis to elucidate potential causes of these divergent results. The mean and standard deviation of the preoperative and 2-year postoperative Oswestry Disability Index (ODI) scores for each study group (laminectomy with fusion and laminectomy alone) were collected from the spondylolisthesis stratum of the Swedish trial and used to create a MATLAB simulator using linear transformations to predict postoperative ODI distributions. Applying this simulator to both varied and published preoperative ODI distributions from the SLIP trial, the authors simulated the results of the US-based trial using treatment effects from the Swedish study and compared simulated US results to those published in the SLIP trial. Simulated US results showed that as preoperative disability increased, the difference in postoperative ODI scores grew between treatment groups and increasingly favored laminectomy alone (p < 0.0001). In 100 simulations of a similarly sized US trial, the average mean change in ODI scores postoperatively was significantly higher than was published for laminectomy alone in the SLIP trial (-21.3 vs -17.9), whereas it was significantly lower than published for fusion (-16.9 vs -26.3). The expected benefit of surgical treatments for spondylolisthesis varied according to preoperative disability. Adapting Swedish-estimated treatment effects to the US context mildly overapproximated the improvement in postoperative disability scores for laminectomy, but more severely underapproximated the improvement reported for laminectomy and fusion in the SLIP trial. The observed heterogeneity between these studies is influenced more by patient response to fusion than response to laminectomy. This analysis paves the way for future studies on the impact of preoperative treatment group heterogeneity, differences in surgical methods, and empirical design on reported clinical benefits. Although bayesian reanalysis of published randomized controlled trial data is susceptible to biases that typically limit post hoc analyses, the authors' method offers a simple and cost-effective approach to improve the understanding of published clinical trial results and their implications for future studies.