Comparison of the erythrocyte sedimentation rate measured in the eye casualty department by the Seditainer method with an automated system

Purpose To compare a new automated system for the measurement of erythrocyte sedimentation rate (ESR) with the established manual Seditainer method. Methods Two hundred and twelve patients undergoing investigation for giant cell arteritis or other systemic vasculitides had ESR measurements by both the established manual Seditainer and the new laboratory-based automated system. The results were compared by correlation coefficient and mean difference. The limits of agreement with confidence intervals were also calculated. Results Across the range of results from 1 to 120 mm/h, the correlation coefficient was 0.844. The automated method had a mean negative bias of -9.8 mm/h (95% confidence interval: -12.2 to -7.4 mm/h). The wide scatter of results produced limits of agreement (+/- 2 standard deviations) between the two methods of -45 to 26 mm/h. There were seven results that were underestimated by the automated system which were clinically significant. Conclusions There is a wide degree of scatter between the two sets of results. The automated system has a negative bias when compared with the manual method. There is a propensity for the automated system to sporadically underestimate the hue result, sometimes to a degree that is clinically significant. The authors therefore cannot recommend replacement of the manual Seditainer system at the present time.