Clinical trials in rheumatoid arthritis: methodological suggestions for assessing radiographs arising from the GRISAR study

OBJECTIVES—The three x ray assessors of the GRISAR study (blinded to treatment) gave consensual erosion and damage scores to the baseline and 12 month radiographs of 284 rheumatoid arthritis (RA) patients using three different methods: single readings (blinded as to patient and chronological sequence of the x rays), paired readings (blinded as to sequence), and chronologically ordered paired readings. The aim was to evaluate which of these reading procedures is the most appropriate for clinical trials. METHODS—The progression of the scores obtained using each procedure was compared by means of descriptive statistics, principal components analysis, and intra-patient correlation coefficients of pairs of methods. Bootstrap estimates of the variance of the difference in the means of two equally sized random samples were calculated to evaluate the power of the statistical analysis performed to assess the possible treatment effect for both paired and chronological reading methods. RESULTS—(a)The standard deviations of the paired and chronological readings were similar, but that of the single readings was higher. (b) The knowledge that two x rays were of the same patient accounted for a sizeable proportion of the between method variability. (c) Agreement was satisfactory between the paired and chronological methods for both scores but, between them and the single readings, it was modest for erosions and poor for damage. (d) The bootstrap estimate of the variance of the difference was smaller for the paired than the chronological method, possibly giving it greater power to test treatment effect. CONCLUSIONS—These results suggested that paired readings were the most suitable for evaluating the progression of joint damage in the GRISAR study.