Study re-evaluated recent work identifying pneumonia and postoperative wound infections (Pn/Wi) as risk markers for impaired long-term functional recovery and survival after spinal cord injury (SCI). The study was considered as a strong statistical analysis. However, some unexplored putative confounders in terms of nonrandom loss to follow-up, temporal changes in clinical practice, and exclusion criteria were found. In order to evaluate and objectivize for the probability of attrition and temporal and selection bias, an array of analytical tools extending beyond the format of the original study were applied. Specifically, to reveal temporal differences in the rate of Pn/Wi, the authors compared the Pn/Wi rate by periods of enrollment (1995–1999 vs 2000–2005) and included the enrollment period as an explanatory variable in the linear models. Based on the results, the authors are convinced that imputation should be preferred to a complete case analysis, which additionally contains sources of biases due to measured confounders.
Author(s):
Kopp, Marcel A. |Martus, Peter |Watzlawick, Ralf DeVivo, Michael J. |Chen, Yuying |Schwab, Jan M.|
