biostudies-literatureUnknown9(4)Ruscitti P<h4>Background</h4>Different patient clusters were preliminarily suggested to dissect the clinical heterogeneity in Still's disease. Thus, we aimed at deriving and validating disease clusters in a multicentre, observational, prospective study to stratify these patients.<h4>Methods</h4>Patients included in GIRRCS AOSD-study group and AIDA Network Still Disease Registry were assessed if variables for cluster analysis were available (age, systemic score, erythrocyte sedimentation rate (ESR), C reactive protein (CRP) and ferritin). K-means algorithm with Euclidean metric and Elbow plot were used to derive an adequate number of clusters.<h4>Results</h4>K-means clustering assessment provided four clusters based on means standardised according to z-scores on 349 patients. All clusters mainly presRMD opene003419https://www.ebi.ac.uk/biostudies/studies/S-EPMC10660445biostudies-literatureDerivation and validation of four patient clusters in Still's disease, results from GIRRCS AOSD-study group and AIDA Network Still Disease Registry.PMC10660445Ruscitti PBerardicurti ODagna LDi Muzio CPerosa FFrediani BRossi SMauro DTufan AMasedu FGidaro AAsfina KDe Stefano LMontecucco CCarubbi FTharwat SLa Torre FGovoni MGiacomelli RRagab GBugatti SPrete MSevik GGuggino GOgunjimi BAtzeni FSfikakis PPSimonini GIagnocco AAntonelli IPBCaggiano VAlmaghlouth IASfriso PDi Cola IMonti SDel Giudice EFabiani CCipriani PLo Gullo AValenti MNavarini LPantano IErten SHinojosa-Azaola AVitale ACiccia FCaso FAlibaz-Oner FCantarini LBartoloni EDireskeneli HGiardini HFotis LHernandez-Rodriguez JMartin-Nares ECosta LIacono DLopalco GMakowska JMaggio MCEmmi GTorres-Ruiz JMaier AfalseDerivation and validation of four patient clusters in Still's disease, results from GIRRCS AOSD-study group and AIDA Network Still Disease Registry.<h4>Background</h4>Different patient clusters were preliminarily suggested to dissect the clinical heterogeneity in Still's disease. Thus, we aimed at deriving and validating disease clusters in a multicentre, observational, prospective study to stratify these patients.<h4>Methods</h4>Patients included in GIRRCS AOSD-study group and AIDA Network Still Disease Registry were assessed if variables for cluster analysis were available (age, systemic score, erythrocyte sedimentation rate (ESR), C reactive protein (CRP) and ferritin). K-means algorithm with Euclidean metric and Elbow plot were used to derive an adequate number of clusters.<h4>Results</h4>K-means clustering assessment provided four clusters based on means standardised according to z-scores on 349 patients. All clusters mainly pres2023-01-01T00:00:00Z2023 Nov2026-07-14T21:00:18.588Z2026-06-24T03:06:56.259ZS-EPMC106604453798932210.1136/rmdopen-2023-003419