Interrater reliability of algometry in measuring pressure pain thresholds in healthy humans, using multiple raters

Objective: To evaluate interrater reliability using 5 newly trained observers in the assessment of pressure pain threshold (PPT) using a fixed-angle algometer. Methods: The study design comprised 2 phases. Phase 1: 5 undergraduate physical therapists were trained in algometry at a predefined angle, at a rate of 5 Newtons (N)/s, to the first dorsal interosseous muscle. Each observer then underwent a competency test of the application speed. The aim was to achieve repeated applications at 5 N/s without visual feedback from the algometer. Phase 2: the 5 observers measured PPT of 13 healthy volunteers, at the first dorsal interosseous muscle. The sequence of observer measurements for each participant was randomized. Mean PPT values for each observer were analyzed using repeated measures analysis of variance, intraclass correlation coefficient (ICC2,1), and standard error of measurement, with 95% confidence intervals (CIs). Results: No significant differences between observers' mean values were found (P = 0.094), suggesting no bias. The ICC was 0.91 (95% CI 0.82, 0.97). The standard error of measurement value was 6.27 N/cm(2) (95% CI 5.35, 7.59). Differences in PPT measurements of more than 17.39 N/cm(2) (1.77 kg/cm(2)) are likely to exceed the magnitude of measurement error, and could be used to indicate true change. This margin of error is, however, somewhat larger than a previously proposed minimum clinically important difference in PPT of 14.71 N/cm(2) (1.5 kg/cm(2)). Discussion: This study provides new evidence that trained observers can apply an algometer at a consistent rate and provide highly reliable measures of PPT in healthy humans, when PPT is calculated as the mean of 3 trials.