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

May Yee Choi; Irene Chen; Ann Elaine Clarke; Marvin J. Fritzler; Katherine A. Buhler; Murray Urowitz; John Hanly; Yvan St-Pierre; Caroline Gordon; Sang Cheol Bae; Juanita Romero-Diaz; Jorge Sanchez-Guerrero; Sasha Bernatsky; Daniel J. Wallace; David Alan Isenberg; Anisur Rahman; Joan T. Merrill; Paul R. Fortin; Dafna D. Gladman; Ian N. Bruce; Michelle Petri; Ellen M. Ginzler; Mary Anne Dooley; Rosalind Ramsey-Goldman; Susan Manzi; Andreas Jönsen; Graciela S. Alarcón; Ronald F. Van Vollenhoven; Cynthia Aranow; Meggan Mackay; Guillermo Ruiz-Irastorza; Sam Lim; Murat Inanc; Kenneth Kalunian; Søren Jacobsen; Christine Peschken; Diane L. Kamen; Anca Askanase; Jill P. Buyon; David Sontag; Karen H. Costenbader

doi:10.1136/ard-2022-223808

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

May Yee Choi^*, Irene Chen, Ann Elaine Clarke, Marvin J. Fritzler, Katherine A. Buhler, Murray Urowitz, John Hanly, Yvan St-Pierre, Caroline Gordon, Sang Cheol Bae, Juanita Romero-Diaz, Jorge Sanchez-Guerrero, Sasha Bernatsky, Daniel J. Wallace, David Alan Isenberg, Anisur Rahman, Joan T. Merrill, Paul R. Fortin, Dafna D. Gladman, Ian N. BruceMichelle Petri, Ellen M. Ginzler, Mary Anne Dooley, Rosalind Ramsey-Goldman, Susan Manzi, Andreas Jönsen, Graciela S. Alarcón, Ronald F. Van Vollenhoven, Cynthia Aranow, Meggan Mackay, Guillermo Ruiz-Irastorza, Sam Lim, Murat Inanc, Kenneth Kalunian, Søren Jacobsen, Christine Peschken, Diane L. Kamen, Anca Askanase, Jill P. Buyon, David Sontag, Karen H. Costenbader

^*Corresponding author for this work

Medicine, Rheumatology Division

Research output: Contribution to journal › Article › peer-review

37 Scopus citations

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.

Original language	English (US)
Pages (from-to)	927-936
Number of pages	10
Journal	Annals of the rheumatic diseases
Volume	82
Issue number	7
DOIs	https://doi.org/10.1136/ard-2022-223808
State	Published - Jul 1 2023

Funding

MYC is supported by the Lupus Foundation of America Gary S. Gilkeson Career Development Award and research gifts in kind from MitogenDx (Calgary, Canada). AEC holds The Arthritis Society Research Chair in Rheumatic Diseases at the University of Calgary. JH\u2019s work was supported by the Canadian Institutes of Health Research (research grant MOP-88526). CG\u2019s work was supported by Lupus UK, Sandwell and West Birmingham Hospitals NHS Trust and the NIHR/Wellcome Trust Clinical Research Facility in Birmingham. S-CB\u2019s work was supported by Basic Science Research Programme through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2021R1A6A1A03038899). The Montreal General Hospital Lupus Clinic is partially supported by the Singer Family Fund for Lupus Research. AR and DAI are supported by the National Institute for Health Research University College London Hospitals Biomedical Research Centre. The Hopkins Lupus Cohort is supported by NIH Grants AR043727 and AR069572. PRF presently holds a tier 1 Canada Research Chair on Systemic Autoimmune Rheumatic Diseases at Universit\u00E9 Laval, and part of this work was done while he was still holding a Distinguished Senior Investigator of The Arthritis Society. INB is an NIHR Senior Investigator and is funded by Arthritis Research UK, the National Institute for Health Research Manchester Biomedical Research Centre and the NIHR/Wellcome Trust Manchester Clinical Research Facility. MAD\u2019s work was supported by the NIH grant RR00046. RR-G\u2019s work was supported by the NIH (grants 1U54TR001353 formerly 8UL1TR000150 and UL-1RR-025741, K24-AR-02318 and P60AR064464 formerly P60-AR-48098). SM is supported by grants R01 AR046588 and K24 AR002213. GR-I is supported by the Department of Education, Universities and Research of the Basque Government. SJ is supported by the Danish Rheumatism Association (A1028) and the Novo Nordisk Foundation (A05990). KHC is supported by NIH K24 AR066109.

Keywords

autoantibodies
autoimmunity
systemic lupus erythematosus

ASJC Scopus subject areas

Rheumatology
Immunology and Allergy
Immunology
General Biochemistry, Genetics and Molecular Biology

Access to Document

10.1136/ard-2022-223808

Cite this

Choi, M. Y., Chen, I., Clarke, A. E., Fritzler, M. J., Buhler, K. A., Urowitz, M., Hanly, J., St-Pierre, Y., Gordon, C., Bae, S. C., Romero-Diaz, J., Sanchez-Guerrero, J., Bernatsky, S., Wallace, D. J., Isenberg, D. A., Rahman, A., Merrill, J. T., Fortin, P. R., Gladman, D. D., ... Costenbader, K. H. (2023). Machine learning identifies clusters of longitudinal autoantibody profiles predictive of systemic lupus erythematosus disease outcomes. Annals of the rheumatic diseases, 82(7), 927-936. https://doi.org/10.1136/ard-2022-223808

@article{bb8d91f8d2d84c0b93b632f75c2baaf6,

title = "Machine learning identifies clusters of longitudinal autoantibody profiles predictive of systemic lupus erythematosus disease outcomes",

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-Sj{\"o}gren syndrome antigen A or Ro60, anti-Sj{\"o}gren 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",

author = "Choi, {May Yee} and Irene Chen and Clarke, {Ann Elaine} and Fritzler, {Marvin J.} and Buhler, {Katherine A.} and Murray Urowitz and John Hanly and Yvan St-Pierre and Caroline Gordon and Bae, {Sang Cheol} and Juanita Romero-Diaz and Jorge Sanchez-Guerrero and Sasha Bernatsky and Wallace, {Daniel J.} and Isenberg, {David Alan} and Anisur Rahman and Merrill, {Joan T.} and Fortin, {Paul R.} and Gladman, {Dafna D.} and Bruce, {Ian N.} and Michelle Petri and Ginzler, {Ellen M.} and Dooley, {Mary Anne} and Rosalind Ramsey-Goldman and Susan Manzi and Andreas J{\"o}nsen and Alarc{\'o}n, {Graciela S.} and {Van Vollenhoven}, {Ronald F.} and Cynthia Aranow and Meggan Mackay and Guillermo Ruiz-Irastorza and Sam Lim and Murat Inanc and Kenneth Kalunian and S{\o}ren Jacobsen and Christine Peschken and Kamen, {Diane L.} and Anca Askanase and Buyon, {Jill P.} and David Sontag and Costenbader, {Karen H.}",

year = "2023",

month = jul,

day = "1",

doi = "10.1136/ard-2022-223808",

language = "English (US)",

volume = "82",

pages = "927--936",

journal = "Annals of the rheumatic diseases",

issn = "0003-4967",

publisher = "Elsevier BV",

number = "7",

}

Choi, MY, Chen, I, Clarke, AE, Fritzler, MJ, Buhler, KA, Urowitz, M, Hanly, J, St-Pierre, Y, Gordon, C, Bae, SC, Romero-Diaz, J, Sanchez-Guerrero, J, Bernatsky, S, Wallace, DJ, Isenberg, DA, Rahman, A, Merrill, JT, Fortin, PR, Gladman, DD, Bruce, IN, Petri, M, Ginzler, EM, Dooley, MA, Ramsey-Goldman, R, Manzi, S, Jönsen, A, Alarcón, GS, Van Vollenhoven, RF, Aranow, C, Mackay, M, Ruiz-Irastorza, G, Lim, S, Inanc, M, Kalunian, K, Jacobsen, S, Peschken, C, Kamen, DL, Askanase, A, Buyon, JP, Sontag, D & Costenbader, KH 2023, 'Machine learning identifies clusters of longitudinal autoantibody profiles predictive of systemic lupus erythematosus disease outcomes', Annals of the rheumatic diseases, vol. 82, no. 7, pp. 927-936. https://doi.org/10.1136/ard-2022-223808

TY - JOUR

T1 - Machine learning identifies clusters of longitudinal autoantibody profiles predictive of systemic lupus erythematosus disease outcomes

AU - Choi, May Yee

AU - Chen, Irene

AU - Clarke, Ann Elaine

AU - Fritzler, Marvin J.

AU - Buhler, Katherine A.

AU - Urowitz, Murray

AU - Hanly, John

AU - St-Pierre, Yvan

AU - Gordon, Caroline

AU - Bae, Sang Cheol

AU - Romero-Diaz, Juanita

AU - Sanchez-Guerrero, Jorge

AU - Bernatsky, Sasha

AU - Wallace, Daniel J.

AU - Isenberg, David Alan

AU - Rahman, Anisur

AU - Merrill, Joan T.

AU - Fortin, Paul R.

AU - Gladman, Dafna D.

AU - Bruce, Ian N.

AU - Petri, Michelle

AU - Ginzler, Ellen M.

AU - Dooley, Mary Anne

AU - Ramsey-Goldman, Rosalind

AU - Manzi, Susan

AU - Jönsen, Andreas

AU - Alarcón, Graciela S.

AU - Van Vollenhoven, Ronald F.

AU - Aranow, Cynthia

AU - Mackay, Meggan

AU - Ruiz-Irastorza, Guillermo

AU - Lim, Sam

AU - Inanc, Murat

AU - Kalunian, Kenneth

AU - Jacobsen, Søren

AU - Peschken, Christine

AU - Kamen, Diane L.

AU - Askanase, Anca

AU - Buyon, Jill P.

AU - Sontag, David

AU - Costenbader, Karen H.

PY - 2023/7/1

Y1 - 2023/7/1

N2 - 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.

AB - 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.

KW - autoantibodies

KW - autoimmunity

KW - systemic lupus erythematosus

UR - http://www.scopus.com/inward/record.url?scp=85160218881&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85160218881&partnerID=8YFLogxK

U2 - 10.1136/ard-2022-223808

DO - 10.1136/ard-2022-223808

M3 - Article

C2 - 37085289

AN - SCOPUS:85160218881

SN - 0003-4967

VL - 82

SP - 927

EP - 936

JO - Annals of the rheumatic diseases

JF - Annals of the rheumatic diseases

IS - 7

ER -

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

Abstract

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this