Interobserver and intraobserver agreement of radiograph interpretation with and without pedicle screw implants: the need for a detailed classification system in posterolateral spinal fusion.

Abstract

A prospective randomized clinical study in which four observers evaluated radiographs of posterolateral fusion masses. To evaluate the accuracy of radiograph interpretation of the posterolateral spinal fusion mass when using a detailed classification system and to analyze the influence of metallic internal fixation devices on radiologic inaccuracy. In general, the literature describing the classification criteria used for radiograph interpretation of spinal posterolateral fusion has serious deficiencies. There is a need for a detailed classification system. Seventy patients were randomly allocated to receive no instrumentation (n = 36) or Cotrel-Dubousset instrumentation (n = 34) in posterolateral lumbar fusion. All four observers participated in a prestudy discussion and evaluated the radiographs (anteroposterior, lateral) taken at the 1-year follow-up evaluation. The observers scored the radiographs twice (30 days apart). Each level on each side was judged separately. A continuous intertransverse bony bridge involving at minimum one of the two sides indicated a fusion at that level. "Fusion" indicated this quality of fusion at all intended levels. If the fusion was doubtful on both sides of the interspace, the individual case could not be classified as "fused." The mean interobserver agreement was 86% (Kappa 0.53), and the mean intraobserver agreement was 93% (Kappa 0.78). No difference in interobserver and intraobserver agreement was found between patients with and without supplementary pedicle screw fixation. All mean Kappa values were classified as fair or good. The four observers identified a mean fusion rate of 81%. It is extremely difficult to interpret radiographic lumbar posterolateral fusion success. Such an assessment needs to be performed by use of a detailed radiographic classification system. The classification system presented here revealed good interobserver and intraobserver agreement, both with and without instrumentation. The classification showed acceptable reliability and may be one way to improve interstudy and intrastudy correlation of radiologic outcomes after posterolateral spinal fusion. Instrumentation did not influence reproducibility but may result in slightly underestimated fusion rates.