Citation

Lu J, Marmarou A, Lapane K. J. Neurotrauma 2012; 29(5): 719-726.

Affiliation

Virginia Commonwealth University, Neurosurgery, Richmond, Virginia, United States; jlu1@vcu.edu.

Copyright

(Copyright © 2012, Mary Ann Liebert Publishers)

DOI

10.1089/neu.2010.1746

PMID

21815785

PMCID

PMC3303101

Abstract

This study extends our previous investigation regarding the effect of nondifferential dichotomous GOS misclassification in TBI clinical trials to the impact of GOS misclassification on ordinal analysis in TBI clinical trials. The impact of 6-month GOS misclassification and ordinal analysis was explored via probabilistic sensitivity analyses using TBI patient datasets contained in the IMPACT database (N=9,205). Three patterns of misclassification were explored with the pre-specified outcome classification error distributions. For the random pattern, we specified a trapezoidal distribution (min: 80%, mode: 85% and 95%, max: 100%) for both sensitivity and specificity; for the upward pattern, the same trapezoidal distribution for sensitivity but with a perfect specificity; and for the downward pattern, the same trapezoidal distribution for specificity but with a perfect sensitivity. The conventional 95% confidence intervals and a simulation interval, which accounts for the misclassification and random errors together, were reported. The results showed that given the specified misclassification distributions, the misclassification with a random or upward pattern would have caused a slightly underestimated 6-month GOS in the observed data. However, the misclassification with a downward pattern would have resulted in an inflated estimation. Thus, the sensitivity analysis suggests that the nondifferential misclassification can cause uncertainties on the primary outcome estimation in TBI trials. However, such effect is likely to be small when ordinal analysis is applied, compared with the impact on the dichotomous GOS situation. The result underlines that the ordinal GOS analysis may gain from both the statistical efficiency, as suggested by several recent TBI and stroke studies, and a relatively smaller impact from the misclassification, as compared with the conventional binary GOS analysis.

Language: en