Machine learning identifies clusters of longitudinal autoantibody profiles predictive of systemic lupus erythematosus disease outcomes

May Yee Choi¹, Irene Chen², Ann Elaine Clarke³, Marvin J Fritzler³, Katherine A Buhler³, Murray Urowitz⁴, John Hanly⁵, Yvan St-Pierre⁶, Caroline Gordon⁷, Sang-Cheol Bae⁸, Juanita Romero-Diaz⁹, Jorge Sanchez-Guerrero¹⁰, Sasha Bernatsky¹¹, Daniel J Wallace¹², David Alan Isenberg¹³, Anisur Rahman¹³, Joan T Merrill¹⁴, Paul R Fortin¹⁵, Dafna D Gladman⁴, Ian N Bruce¹⁶, Michelle Petri¹⁷, Ellen M Ginzler¹⁸, Mary Anne Dooley¹⁹, Rosalind Ramsey-Goldman²⁰, Susan Manzi²¹, Andreas Jönsen²², Graciela S Alarcón²³, Ronald F van Vollenhoven²⁴, Cynthia Aranow²⁵, Meggan Mackay²⁵, Guillermo Ruiz-Irastorza²⁶, Sam Lim²⁷, Murat Inanc²⁸, Kenneth Kalunian²⁹, Søren Jacobsen³⁰, Christine Peschken³¹, Diane L Kamen³², Anca Askanase³³, Jill P Buyon³⁴, David Sontag², Karen H Costenbader^{35

36}

Affiliations

¹ Medicine, University of Calgary Cumming School of Medicine, Calgary, Alberta, Canada may.choi@ucalgary.ca.
² Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA.
³ Medicine, University of Calgary Cumming School of Medicine, Calgary, Alberta, Canada.
⁴ Center for Prognosis Studies in the Rheumatic Diseases, Toronto Western Hospital, University of Toronto, Lupus Clinic, Toronto, Ontario, Canada.
⁵ Division of Rheumatology, Department of Medicine and Department of Pathology, Queen Elizabeth II Health Sciences Centre and Dalhousie University, Halifax, Nova Scotia, Canada.
⁶ Medicine, Research Institute of the McGill University Health Center, Montreal, Quebec, Canada.
⁷ Rheumatology Research Group, Institute of Inflammation and Ageing, College of Medical and Dental Sciences, Birmingham University Medical School, Birmingham, West Midlands, UK.
⁸ Rheumatology, Hanyang University Hospital for Rheumatic Diseases, Hanyang University Institute for Rheumatology and Hanyang University Institute of Bioscience and Biotechnology, Seoul, The Republic of Korea.
⁹ Immunology and Rheumatology, Instituto Nacional de Ciencias Médicas y Nutrición, Mexico City, Mexico.
¹⁰ Mount Sinai Hospital and University Health Network, University of Toronto, Toronto, Ontario, Canada.
¹¹ Divisions of Rheumatology and Clinical Epidemiology, McGill University Health Centre, Montreal, Quebec, Canada.
¹² Division of Rheumatology, Cedars-Sinai/David Geffen School of Medicine at UCLA, Los Angeles, California, USA.
¹³ Centre for Rheumatology, Department of Medicine, University College London, London, UK.
¹⁴ Department of Clinical Pharmacology, Oklahoma Medical Research Foundation, Oklahoma City, Oklahoma, USA.
¹⁵ Division of Rheumatology, CHU de Québec - Université Laval, Quebec City, Quebec, Canada.
¹⁶ Epidemiology Unit, University of Manchester, Manchester, UK.
¹⁷ Division of Rheumatology, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
¹⁸ Department of Medicine, SUNY Downstate Medical Center, Brooklyn, New York, USA.
¹⁹ Thurston Arthritis Research Center, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA.
²⁰ Department of Medicine, Division of Rheumatology, Northwestern University and Feinberg School of Medicine, Chicago, Illinois, USA.
²¹ Medicine, Allegheny Health Network, Pittsburgh, Pennsylvania, USA.
²² Clinical Sciences, Lund University, Lund, Sweden.
²³ Department of Medicine, The University of Alabama at Birmingham Heersink School of Medicine, Birmingham, Alabama, USA.
²⁴ Rheumatology & Immunology Center, University of Amsterdam, Amsterdam, The Netherlands.
²⁵ Division of Autoimmune and Musculoskeletal Disease, Feinstein Institute for Medical Research, Manhasset, New York, USA.
²⁶ Autoimmune Diseases Research Unit, Department of Internal Medicine, BioCruces Health Research Institute, Hospital Universitario Cruces, University of the Basque Country, Barakaldo, Spain.
²⁷ Division of Rheumatology, Emory University School of Medicine, Atlanta, Georgia, USA.
²⁸ Department of Internal Medicine, Division of Rheumatology, Istanbul University, Istanbul Medical Faculty, Istanbul, Turkey.
²⁹ Department of Rheumatology, Allergy and Immunology, University of California San Diego, La Jolla, California, USA.
³⁰ Department of Rheumatology, Rigshospitalet, Copenhagen University Hospital, Copenhagen, Denmark.
³¹ Internal Medicine, University of Manitoba, Winnipeg, Manitoba, Canada.
³² Division of Rheumatology & Immunology, Medical University of South Carolina, Charleston, South Carolina, USA.
³³ Hospital for Joint Diseases, New York University, Seligman Centre for Advanced Therapeutics, New York, New York, USA.
³⁴ Division of Rheumatology, New York University School of Medicine, New York, New York, USA.
³⁵ Department of Medicine, Division of Rheumatology, Inflammation and Immunity, Brigham and Women's Hospital, Boston, Massachusetts, USA.
³⁶ Medicine, Harvard Medical School, Boston, Massachusetts, USA.

PMID: 37085289
PMCID: PMC11293954
DOI: 10.1136/ard-2022-223808

Machine learning identifies clusters of longitudinal autoantibody profiles predictive of systemic lupus erythematosus disease outcomes

May Yee Choi et al. Ann Rheum Dis. 2023 Jul.

. 2023 Jul;82(7):927-936.

doi: 10.1136/ard-2022-223808. Epub 2023 Apr 21.

Authors

Affiliations

¹ Medicine, University of Calgary Cumming School of Medicine, Calgary, Alberta, Canada may.choi@ucalgary.ca.
² Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA.
³ Medicine, University of Calgary Cumming School of Medicine, Calgary, Alberta, Canada.
⁴ Center for Prognosis Studies in the Rheumatic Diseases, Toronto Western Hospital, University of Toronto, Lupus Clinic, Toronto, Ontario, Canada.
⁵ Division of Rheumatology, Department of Medicine and Department of Pathology, Queen Elizabeth II Health Sciences Centre and Dalhousie University, Halifax, Nova Scotia, Canada.
⁶ Medicine, Research Institute of the McGill University Health Center, Montreal, Quebec, Canada.
⁷ Rheumatology Research Group, Institute of Inflammation and Ageing, College of Medical and Dental Sciences, Birmingham University Medical School, Birmingham, West Midlands, UK.
⁸ Rheumatology, Hanyang University Hospital for Rheumatic Diseases, Hanyang University Institute for Rheumatology and Hanyang University Institute of Bioscience and Biotechnology, Seoul, The Republic of Korea.
⁹ Immunology and Rheumatology, Instituto Nacional de Ciencias Médicas y Nutrición, Mexico City, Mexico.
¹⁰ Mount Sinai Hospital and University Health Network, University of Toronto, Toronto, Ontario, Canada.
¹¹ Divisions of Rheumatology and Clinical Epidemiology, McGill University Health Centre, Montreal, Quebec, Canada.
¹² Division of Rheumatology, Cedars-Sinai/David Geffen School of Medicine at UCLA, Los Angeles, California, USA.
¹³ Centre for Rheumatology, Department of Medicine, University College London, London, UK.
¹⁴ Department of Clinical Pharmacology, Oklahoma Medical Research Foundation, Oklahoma City, Oklahoma, USA.
¹⁵ Division of Rheumatology, CHU de Québec - Université Laval, Quebec City, Quebec, Canada.
¹⁶ Epidemiology Unit, University of Manchester, Manchester, UK.
¹⁷ Division of Rheumatology, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
¹⁸ Department of Medicine, SUNY Downstate Medical Center, Brooklyn, New York, USA.
¹⁹ Thurston Arthritis Research Center, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA.
²⁰ Department of Medicine, Division of Rheumatology, Northwestern University and Feinberg School of Medicine, Chicago, Illinois, USA.
²¹ Medicine, Allegheny Health Network, Pittsburgh, Pennsylvania, USA.
²² Clinical Sciences, Lund University, Lund, Sweden.
²³ Department of Medicine, The University of Alabama at Birmingham Heersink School of Medicine, Birmingham, Alabama, USA.
²⁴ Rheumatology & Immunology Center, University of Amsterdam, Amsterdam, The Netherlands.
²⁵ Division of Autoimmune and Musculoskeletal Disease, Feinstein Institute for Medical Research, Manhasset, New York, USA.
²⁶ Autoimmune Diseases Research Unit, Department of Internal Medicine, BioCruces Health Research Institute, Hospital Universitario Cruces, University of the Basque Country, Barakaldo, Spain.
²⁷ Division of Rheumatology, Emory University School of Medicine, Atlanta, Georgia, USA.
²⁸ Department of Internal Medicine, Division of Rheumatology, Istanbul University, Istanbul Medical Faculty, Istanbul, Turkey.
²⁹ Department of Rheumatology, Allergy and Immunology, University of California San Diego, La Jolla, California, USA.
³⁰ Department of Rheumatology, Rigshospitalet, Copenhagen University Hospital, Copenhagen, Denmark.
³¹ Internal Medicine, University of Manitoba, Winnipeg, Manitoba, Canada.
³² Division of Rheumatology & Immunology, Medical University of South Carolina, Charleston, South Carolina, USA.
³³ Hospital for Joint Diseases, New York University, Seligman Centre for Advanced Therapeutics, New York, New York, USA.
³⁴ Division of Rheumatology, New York University School of Medicine, New York, New York, USA.
³⁵ Department of Medicine, Division of Rheumatology, Inflammation and Immunity, Brigham and Women's Hospital, Boston, Massachusetts, USA.
³⁶ Medicine, Harvard Medical School, Boston, Massachusetts, USA.

PMID: 37085289
PMCID: PMC11293954
DOI: 10.1136/ard-2022-223808

Abstract

Objectives: A 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.

Methods: Demographic, 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.

Results: Cluster 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.

Conclusion: Four discrete SLE patient longitudinal autoantibody clusters were predictive of long-term disease activity, organ involvement, treatment requirements and mortality risk.

Keywords: autoantibodies; autoimmunity; systemic lupus erythematosus.

PubMed Disclaimer

Conflict of interest statement

Competing interests: MYC has received consulting fees from Janssen, AstraZeneca, Mallinckrodt Pharmaceuticals and MitogenDx. AEC has received consulting fees, speaking fees and/or honoraria from AstraZeneca, Bristol Myers Squibb and GlaxoSmithKline (<US$10 000 each) and research support from GlaxoSmithKline. MJF is Director of Mitogen Diagnostics (Calgary, Alberta, Canada) and a consultant to Werfen International (San Diego, California, USA; Barcelona, Spain), Aesku Group (Wendelsheim, Germany) and Alexion Canada (<US$10 000). CG has received consulting fees, speaking fees and/or honoraria from Eli Lilly, UCB, GlaxoSmithKline, Merck Serono and BMS (<US$10 000 each) and grants from UCB. Grants from UCB were not to CG but to Sandwell and West Birmingham Hospitals NHS Trust. DDG received consulting fees, speaking fees and/or honoraria from GlaxoSmithKline (<US$10 000). INB has received consulting fees, speaking fees and/or honoraria from Eli Lilly, UCB, Roche, Merck Serono, MedImmune (<US$10 000 each) and grants from UCB, Genzyme Sanofi and GlaxoSmithKline. EMG has paid consultation with investment analysts Guidepoint Global Gerson Lerman Group. KK has received grants from UCB, Human Genome Sciences/GlaxoSmithKline, Takeda, Ablynx, Bristol Myers Squibb, Pfizer and Kyowa Hakko Kirin, and has received consulting fees from Exagen Diagnostics, Genentech, Eli Lilly, Bristol Myers Squibb and Anthera (<US$10 000 each). KHC has consulted for or collaborated on research projects with Janssen, GlaxoSmithKline, Gilead, Exagen Diagnostics, Lilly, Merck, AstraZeneca, Amgen and Neutrolis (<US$10 000 each). The remainder of the authors have no disclosures.

Figures

**Figure 1.. Four autoantibody cluster groups identified among 805 SLE patients followed from enrolment through years 3 and 5.**
Latent space visualized using a t-distributed stochastic neighbor embedding (t-SNE) with colors based on cluster labels.

**Figure 2.. Autoantibody profile of 805 SLE patients in order of most prevalent autoantibodies in A) Cluster 1, B) Cluster 2, C) Cluster 3, D) Cluster 4.**
Standard deviation bars have been removed to make graphs easier to visualize.

**Figure 3.. ANA titres and patterns for each cluster.**
A) Mean maximum ANA titers slightly decreased over time. Cluster 1 (anti-Sm/RNP) highest mean maximum ANA titer. Cluster 2 (low anti-dsDNA) lowest mean maximum ANA titer. B) AC-1 (homogeneous pattern associated with anti-dsDNA, histones), AC-4 (fine speckled associated with anti-SSA/Ro60, anti-SSB/La), and AC- 19 (cytoplasmic dense fine speckled associated with anti-ribosomal P) correspond to the autoantibody profile observed in cluster 4. High titres of AC-5 (large specked associated with anti-Sm and anti-U1RNP antibodies) correspond to cluster 1 antibody profile. Remaining AC patterns had mean titers <1:80 at all three visits for all cluster groups.

See this image and copyright information in PMC

References

1. Budde P, Zucht HD, Vordenbäumen S, Goehler H, Fischer-Betz R, Gamer M, et al. Multiparametric detection of autoantibodies in systemic lupus erythematosus. Lupus. 2016;25(8):812–22. - PubMed
1. Mizus M, Li J, Goldman D, Petri MA. Autoantibody clustering of lupus-associated pulmonary hypertension. Lupus Sci Med. 2019;6(1):e000356. - PMC - PubMed
1. To CH, Petri M. Is antibody clustering predictive of clinical subsets and damage in systemic lupus erythematosus? Arthritis Rheum. 2005;52(12):4003–10. - PubMed
1. Tápanes FJ, Vásquez M, Ramírez R, Matheus C, Rodríguez MA, Bianco N. Cluster analysis of antinuclear autoantibodies in the prognosis of SLE nephropathy: are anti-extractable nuclear antibodies protective? Lupus. 2000;9(6):437–44. - PubMed
1. Pacheco Y, Barahona-Correa J, Monsalve DM, Acosta-Ampudia Y, Rojas M, Rodríguez Y, et al. Cytokine and autoantibody clusters interaction in systemic lupus erythematosus. J Transl Med. 2017;15(1):239. - PMC - PubMed

Publication types

Actions
Actions

MeSH terms

Actions
Actions
Actions
Actions
Actions
Actions
Actions

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Machine learning identifies clusters of longitudinal autoantibody profiles predictive of systemic lupus erythematosus disease outcomes

Affiliations

Machine learning identifies clusters of longitudinal autoantibody profiles predictive of systemic lupus erythematosus disease outcomes

Authors

Affiliations

Abstract

Conflict of interest statement

Figures

References

Publication types

MeSH terms

Substances

Grants and funding

LinkOut - more resources

Full Text Sources

Medical