Cluster analysis of paediatric Behçet's disease: Data from The Pediatric Rheumatology Academy-Research Group.

OBJECTIVES: Behçet's disease (BD) is a systemic vasculitis affecting many organ systems, with the involvement of all-sized arteries and veins. The study aims to determine the main characteristics of paediatric BD patients and also analyse the clustering phenotypes. METHODS: Demographic data, clinical manifestations, laboratory features, treatment schedules, and disease outcomes were achieved from patients' charts retrospectively. A cluster analysis was performed according to the phenotype. RESULTS: A total of 225 (109 male/116 female) patients with BD were enrolled in the study. The median ages of disease onset and diagnosis were 131 (36-151) and 156 (36-192) months, respectively. According to cluster analysis, 132 (58.6%) patients belonged to the mucocutaneous-only cluster (C1), while 35 (15.6%) patients fitted to articular type (C2), 25 (11.1%) were in the ocular cluster (C3), 26 (11.6%) were in the vascular cluster (C4), and 7(3.1%) belonged to the gastrointestinal cluster (C5). Ocular and vascular clusters were more common in boys (p < .001), while girls usually presented with the mucocutaneous-only cluster. The disease activity at the diagnosis and the last control was higher in ocular, vascular, and gastrointestinal clusters. CONCLUSIONS: These identified juvenile BD clusters express different phenotypes with different outcomes Our analysis may help clinicians to identify the disease subtypes accurately and to arrange personalized treatment.

Diagnosing growing pains in children by using machine learning: a cross-sectional multicenter study.

Growing pains (GP) are the most common cause of recurrent musculoskeletal pain in children. There are no diagnostic criteria for GP. We aimed at analyzing GP-related characteristics and assisting GP diagnosis by using machine learning (ML). Children with GP and diseased controls were enrolled between February and August 2019. ML models were developed by using tenfold cross-validation to classify GP patients. A total of 398 patients with GP (F/M:1.3; median age 102 months) and 254 patients with other diseases causing limb pain were enrolled. The pain was bilateral (86.2%), localized in the lower extremities (89.7%), nocturnal (74%), and led to awakening at night (60.8%) in most GP patients. History of arthritis, trauma, morning stiffness, limping, limitation of activities, and school abstinence were more prevalent among controls than in GP patients (p = 0.016 for trauma; p < 0.001 for others). The experiments with different ML models revealed that the Random Forest algorithm had the best performance with 0.98 accuracy, 0.99 sensitivity, and 0.97 specificity for GP diagnosis. This is the largest cohort study of children with GP and the first study that attempts to diagnose GP by using ML techniques. Our ML model may be used to facilitate diagnosing GP.

The feasibility of withdrawing canakinumab in paediatric colchicine-resistant familial Mediterranean fever patients.

OBJECTIVES: To determine the feasibility of withdrawing canakinumab (CAN) in a large cohort of paediatric patients with colchicine-resistant familial Mediterranean fever (crFMF). METHODS: This retrospective observational cohort study included paediatric crFMF patients that received CAN treatment for ≥6 months. Patient data were recorded at treatment onset (baseline), and at 1, 3, 6, 12, 18, and 24 months after initiation of treatment. RESULTS: The study included 114 patients that were followed-up for 2736 person-months. During the 24-month follow-up period, the CAN dose interval remained unchanged in 44 patients. The dose interval was extended in 58 patients within a median 6 months (range: 3-18 months) of treatment initiation. In all, 4 of these 58 patients had a new attack of crFMF after the dose interval was extended. CAN was withdrawn in 12 patients (in 5 at month 12 month and in 7 at month 18), of which 2 had a new attack within 3 months of withdrawal. In these 2 patients CAN was re-initiated with a dose interval of 8 weeks. The remaining 10 patients in which CAN was withdrawn did not report any symptoms throughout the remainder of the 24-month follow-up period. The median attack-free period in those treated with CAN was 669 d (95% CI: 644-696). CONCLUSIONS: The present findings show that it may be feasible to withdraw CAN or extend its dose interval in paediatric crFMF patients. Based on the present findings, we think that as the quantity of real-life data increases, standard CAN protocols may be developed.