Machine learning identifies clusters of longitudinal autoantibody profiles predictive of systemic lupus erythematosus disease outcomes
-
Published:2023-04-21
Issue:7
Volume:82
Page:927-936
-
ISSN:0003-4967
-
Container-title:Annals of the Rheumatic Diseases
-
language:en
-
Short-container-title:Ann Rheum Dis
Author:
Choi May YeeORCID, Chen Irene, Clarke Ann Elaine, Fritzler Marvin JORCID, Buhler Katherine A, Urowitz MurrayORCID, Hanly John, St-Pierre Yvan, Gordon Caroline, Bae Sang-CheolORCID, Romero-Diaz Juanita, Sanchez-Guerrero Jorge, Bernatsky SashaORCID, Wallace Daniel JORCID, Isenberg David AlanORCID, Rahman AnisurORCID, Merrill Joan T, Fortin Paul RORCID, Gladman Dafna DORCID, Bruce Ian N, Petri MichelleORCID, Ginzler Ellen M, Dooley Mary Anne, Ramsey-Goldman Rosalind, Manzi Susan, Jönsen Andreas, Alarcón Graciela SORCID, van Vollenhoven Ronald FORCID, Aranow CynthiaORCID, Mackay Meggan, Ruiz-Irastorza GuillermoORCID, Lim Sam, Inanc MuratORCID, Kalunian Kenneth, Jacobsen Søren, Peschken Christine, Kamen Diane L, Askanase Anca, Buyon Jill P, Sontag David, Costenbader Karen HORCID
Abstract
ObjectivesA novel longitudinal clustering technique was applied to comprehensive autoantibody data from a large, well-characterised, multinational inception systemic lupus erythematosus (SLE) cohort to determine profiles predictive of clinical outcomes.MethodsDemographic, clinical and serological data from 805 patients with SLE obtained within 15 months of diagnosis and at 3-year and 5-year follow-up were included. For each visit, sera were assessed for 29 antinuclear antibodies (ANA) immunofluorescence patterns and 20 autoantibodies. K-means clustering on principal component analysis-transformed longitudinal autoantibody profiles identified discrete phenotypic clusters. One-way analysis of variance compared cluster enrolment demographics and clinical outcomes at 10-year follow-up. Cox proportional hazards model estimated the HR for survival adjusting for age of disease onset.ResultsCluster 1 (n=137, high frequency of anti-Smith, anti-U1RNP, AC-5 (large nuclear speckled pattern) and high ANA titres) had the highest cumulative disease activity and immunosuppressants/biologics use at year 10. Cluster 2 (n=376, low anti-double stranded DNA (dsDNA) and ANA titres) had the lowest disease activity, frequency of lupus nephritis and immunosuppressants/biologics use. Cluster 3 (n=80, highest frequency of all five antiphospholipid antibodies) had the highest frequency of seizures and hypocomplementaemia. Cluster 4 (n=212) also had high disease activity and was characterised by multiple autoantibody reactivity including to antihistone, anti-dsDNA, antiribosomal P, anti-Sjögren syndrome antigen A or Ro60, anti-Sjögren syndrome antigen B or La, anti-Ro52/Tripartite Motif Protein 21, antiproliferating cell nuclear antigen and anticentromere B). Clusters 1 (adjusted HR 2.60 (95% CI 1.12 to 6.05), p=0.03) and 3 (adjusted HR 2.87 (95% CI 1.22 to 6.74), p=0.02) had lower survival compared with cluster 2.ConclusionFour discrete SLE patient longitudinal autoantibody clusters were predictive of long-term disease activity, organ involvement, treatment requirements and mortality risk.
Funder
LUPUS UK Korea Healthcare Arthritis Society Canada Research Chairs Department of Education, Universities and Research of the Basque Government Gigtforeningen Canadian Institutes of Health Research Ministry for Health and Welfare, Republic of Korea National Institute for Health Research Manchester Biomedical Research Centre Novo Nordisk Foundation Singer Family Fund for Lupus Research Sandwell and West Birmingham Hospitals NHS Trust Wellcome Trust National Research Foundation of Korea Lupus Foundation of America National Institute for Health Research London Hospitals Biomedical Research Centre
Subject
General Biochemistry, Genetics and Molecular Biology,Immunology,Immunology and Allergy,Rheumatology
Cited by
26 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|