Lupus & antiphospholipid syndrome
Which extra-renal flare is ‘difficult to treat’ in systemic lupus erythematosus? A one-year longitudinal study comparing traditional and machine learning approaches
Authors' conclusion
Our clusterization well separates extra-renal flares according to their baseline features and may propose a new identification standard.
Study context
- Population
- Extra-renal flares in SLE patients of the authors' cohort, 2015–2021, with at least one year of follow-up
- Participants
- 79 extra-renal flares
- Exposure
- Difficult to treat (D2T) vs non-D2T extra-renal flares; clusters of flares by baseline features
- Outcome
- Attainment of remission and LLDAS; D2T flare defined as non-attainment of LLDAS at 6 and 12 months
- Follow-up
- 12 months
Methodological detailsone-year follow-up, cluster analysis, machine learning model, 420 SLE patients in cohort; 114 flares 2015–2021
- One-year follow-up
- Cluster analysis
- Machine learning model
- 420 SLE patients in cohort; 114 flares 2015–2021
Main finding
As reported in the abstract
Flare outcomes at 12 months
In LLDAS
79.4%
In remission
49.4%
D2T flares
17
21.5%
Observational data: associations, not effects.
Further findings
Flare phenotypes
- Mucocutaneous
- 24.1%
- Musculoskeletal
- 45.6%
Clusters and predictors of D2T flares
- Cluster 'D' (mild-moderate mucocutaneous flares, history of skin involvement) had the lowest remission rate
- Not being in LLDAS at 3 months was the unique independent predictor of D2T flares
- D2T flares received higher cumulative and daily glucocorticoid (GC) dose
Original publication
Which extra-renal flare is ‘difficult to treat’ in systemic lupus erythematosus? A one-year longitudinal study comparing traditional and machine learning approaches. Rheumatology (Oxford). Published 24 April 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →