A stratified approach to juvenile idiopathic arthritis: leveraging machine learning to uncover subgroups of patients following treatment with etanercept.

In 1003 children and young people, five clusters were identified following etanercept initiation.

In three clusters, JADAS components changed in parallel: fast improvers (16%), slow improvers (10%) and persistent disease (37%).

In two, all components except for one improved over time: persistent physician global assessment (7%) and persistent parent global evaluation (30%).

There was high consistency (73%) of children and young people having a persistent parent global evaluation pattern following both drugs.