@article {Terslev2177, author = {Lene Terslev and Marwin Gutierrez and Wolfgang A. Schmidt and Helen I. Keen and Emilio Filippucci and David Kane and Ralf Thiele and Gurjit Kaeley and Peter Balint and Peter Mandl and Andrea Delle Sedie and Hilde Berner Hammer and Robin Christensen and Ingrid M{\"o}ller and Carlos Pineda and Eugene Kissin and George A. Bruyn and Annamaria Iagnocco and Esperanza Naredo and Maria Antonietta D{\textquoteright}Agostino}, editor = {Aegerter, Philippe and Aydin, Sibel and Backhaus, Marina and Bong, David and Chary-Valckenaere, Isabelle and Collado, Paz and De Miguel, Eugenio and Dejaco, Christian and Epis, Oscar and Freeston, Jane E. and Gandjbakhch, Frederique and Grassi, Walter and Hanova, Petra and Jousse-Joulin, Sandrine and Joshua, Fredrick and Koski, Juhani and Loeuille, Damien and Ravagnani, Viviana and Reginato, Anthony and Sharp, Veronica and Swen, Nanno and Szkudlarek, Marcin and Wakefield, Richard J. and Ziswiler, Hans-Rudolf}, title = {Ultrasound as an Outcome Measure in Gout. A Validation Process by the OMERACT Ultrasound Working Group}, volume = {42}, number = {11}, pages = {2177--2181}, year = {2015}, doi = {10.3899/jrheum.141294}, publisher = {The Journal of Rheumatology}, abstract = {Objective. To summarize the work performed by the Outcome Measures in Rheumatology (OMERACT) Ultrasound (US) Working Group on the validation of US as a potential outcome measure in gout.Methods. Based on the lack of definitions, highlighted in a recent literature review on US as an outcome tool in gout, a series of iterative exercises were carried out to obtain consensus-based definitions on US elementary components in gout using a Delphi exercise and subsequently testing these definitions in static images and in patients with proven gout. Cohen{\textquoteright}s κ was used to test agreement, and values of 0{\textendash}0.20 were considered poor, 0.20{\textendash}0.40 fair, 0.40{\textendash}0.60 moderate, 0.60{\textendash}0.80 good, and 0.80{\textendash}1 excellent.Results. With an agreement of \> 80\%, consensus-based definitions were obtained for the 4 elementary lesions highlighted in the literature review: tophi, aggregates, erosions, and double contour (DC). In static images interobserver reliability ranged from moderate to almost perfect, and similar results were found for the intrareader reliability. In patients the intraobserver agreement was good for all lesions except DC (moderate). The interobserver agreement was poor for aggregates and DC but moderate for the other components.Conclusion. These first steps in evaluating the validity of US as an outcome measure for gout show that the reliability of the definitions ranged from moderate to excellent in static images and somewhat lower in patients, indicating that a standardized scanning technique may be needed, before testing the responsiveness of those definitions in a composite US score.}, issn = {0315-162X}, URL = {https://www.jrheum.org/content/42/11/2177}, eprint = {https://www.jrheum.org/content/42/11/2177.full.pdf}, journal = {The Journal of Rheumatology} }