The Florida Scoring System for stratifying children with suspected Sjögren's disease: a cross-sectional machine learning study
Authors' conclusion
The Florida Scoring System is a paediatrician-friendly tool that can be used to assist classification and long-term monitoring of suspected childhood Sjögren's disease.
Study context
- Population
- Symptomatic patients <18 years or with symptom onset before 18 years with suspected childhood SjD, Department of Pediatric Rheumatology, University of Florida, USA; median age at diagnosis 15 years (IQR 11–17)243 recruited
- Participants
- 217 patients
- Exposure
- Class I vs Class II vs Class III
- Class In = 27
- Class IIn = 98
- Class IIIn = 92
- Outcome
- Patient classes identified by latent class analysis and their prediction by machine learning models (Florida Scoring System)
Methodological detailsmachine learning, latent class analysis, causal graph learning, single-centre, Patients screened Jan 16, 2018, to April 28, 2022: 448 screened
- Machine learning
- Latent class analysis
- Causal graph learning
- Single-centre
- Patients screened Jan 16, 2018, to April 28, 2022: 448 screened
Main finding
As reported in the abstract
Patient classes (latent class analysis)
- Three distinct patient classes identified
- Machine learning models accurately predicted patient class and ranked variable importance consistently
- Causal graphical model discovered key features for constructing the Florida Scoring System
Observational data: associations, not effects.
Original publication
The Florida Scoring System for stratifying children with suspected Sjögren's disease: a cross-sectional machine learning study. Lancet Rheumatol. Published May 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →