Biomarkers of erosive arthritis in systemic lupus erythematosus: Application of machine learning models

• Published in: PloS one Vol. 13; no. 12; p. e0207926
• Main Authors: Ceccarelli, Fulvia, Sciandrone, Marco, Perricone, Carlo, Galvan, Giulio, Cipriano, Enrica, Galligari, Alessandro, Levato, Tommaso, Colasanti, Tania, Massaro, Laura, Natalucci, Francesco, Spinelli, Francesca Romana, Alessandri, Cristiano, Valesini, Guido, Conti, Fabrizio
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 04.12.2018; Public Library of Science (PLoS)
• Subjects: Adult; Alzheimer's disease; Anti-Citrullinated Protein Antibodies - blood; Antibodies; Arthralgia; Arthritis; Arthritis - diagnostic imaging; Arthritis - etiology; Arthritis - immunology; Artificial intelligence; Autoantibodies - blood; Autoimmune diseases; Biological markers; Biology and Life Sciences; Biomarkers; Biomarkers - blood; Carp; Chronic conditions; Citrulline; Cohort Studies; Computer and Information Sciences; Cross-Sectional Studies; Damage detection; Decision Trees; Development and progression; Diagnosis; Diagnostic imaging; Engineering and Technology; Family medical history; Female; Humans; Immunoglobulins; Joint diseases; Laboratories; Learning algorithms; Logistic Models; Lupus; Lupus erythematosus; Lupus Erythematosus, Systemic - complications; Lupus Erythematosus, Systemic - immunology; Lymphoma; Machine Learning; Male; Medicine and Health Sciences; Middle Aged; NMR; Nuclear magnetic resonance; Patients; Peptides; Phenotypes; Protein Carbamylation - immunology; Proteins; Research and Analysis Methods; Rheumatoid arthritis; Rheumatoid factor; Rheumatoid Factor - blood; Rheumatology; Risk Factors; Systemic lupus erythematosus; Ultrasonic imaging; Ultrasonography; Ultrasound; Ultrasound imaging; United States > US; Italy
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0207926

Limited evidences are available on biomarkers to recognize Systemic Lupus erythematosus (SLE) patients at risk to develop erosive arthritis. Anti-citrullinated peptide antibodies (ACPA) have been widely investigated and identified in up to 50% of X-ray detected erosive arthritis; conversely, few studies evaluated anti-carbamylated proteins antibodies (anti-CarP). Here, we considered the application of machine learning models to identify relevant factors in the development of ultrasonography (US)-detected erosive damage in a large cohort of SLE patients with joint involvement. We enrolled consecutive SLE patients with arthritis/arthralgia. All patients underwent joint (DAS28, STR) and laboratory assessment (detection of ACPA, anti-CarP, Rheumatoid Factor, SLE-related antibodies). The bone surfaces of metacarpophalangeal and proximal interphalangeal joints were assessed by US: the presence of erosions was registered with a dichotomous value (0/1), obtaining a total score (0-20). Concerning machine learning techniques, we applied and compared Logistic Regression and Decision Trees in conjunction with the feature selection Forward Wrapper method. We enrolled 120 SLE patients [M/F 8/112, median age 47.0 years (IQR 15.0); median disease duration 120.0 months (IQR 156.0)], 73.3% of them referring at least one episode of arthritis. Erosive damage was identified in 25.8% of patients (mean±SD 0.7±1.6), all of them with clinically evident arthritis. We applied Logistic Regression in conjunction with the Forward Wrapper method, obtaining an AUC value of 0.806±0.02. As a result of the learning procedure, we evaluated the relevance of the different factors: this value was higher than 35% for ACPA and anti-CarP. The application of Machine Learning Models allowed to identify factors associated with US-detected erosive bone damage in a large SLE cohort and their relevance in determining this phenotype. Although the scope of this study is limited by the small sample size and its cross-sectional nature, the results suggest the relevance of ACPA and anti-CarP antibodies in the development of erosive damage as also pointed out in other studies.