Dataset Information

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-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.

SUBMITTER: Choi MY

PROVIDER: S-EPMC11293954 | biostudies-literature | 2023 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Choi May Yee MY Chen Irene I Clarke Ann Elaine AE Fritzler Marvin J MJ Buhler Katherine A KA Urowitz Murray M Hanly John J St-Pierre Yvan Y Gordon Caroline C Bae Sang-Cheol SC Romero-Diaz Juanita J Sanchez-Guerrero Jorge J Bernatsky Sasha S Wallace Daniel J DJ Isenberg David Alan DA Rahman Anisur A Merrill Joan T JT Fortin Paul R PR Gladman Dafna D DD Bruce Ian N IN Petri Michelle M Ginzler Ellen M EM Dooley Mary Anne MA Ramsey-Goldman Rosalind R Manzi Susan S Jönsen Andreas A Alarcón Graciela S GS van Vollenhoven Ronald F RF Aranow Cynthia C Mackay Meggan M Ruiz-Irastorza Guillermo G Lim Sam S Inanc Murat M Kalunian Kenneth K Jacobsen Søren S Peschken Christine C Kamen Diane L DL Askanase Anca A Buyon Jill P JP Sontag David D Costenbader Karen H KH

Annals of the rheumatic diseases 20230421 7

<h4>Objectives</h4>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.<h4>Methods</h4>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 antibodie ...[more]

PMID: 37085289

Similar Datasets

Project description:Systemic lupus erythematosus is a chronic autoimmune disease of complex clinical presentation and etiology and is likely influenced by numerous genetic and environmental factors. While a large number of susceptibility genes have been identified, the production of antibodies against a distinct subset of nuclear proteins remains a primary distinguishing characteristic in disease diagnosis. However, the utility of autoantibody biomarkers for disease sub-classification and grouping remains elusive, in part, because of the difficulty in large scale profiling using a uniform, quantitative platform. In the present study serological profiles of several known SLE antigens, including Sm-D3, RNP-A, RNP-70k, Ro52, Ro60, and La, as well as other cytokine and neuronal antigens were obtained using the luciferase immunoprecipitation systems (LIPS) approach. The resulting autoantibody profiles revealed that 88% of a pilot cohort and 98% of a second independent cohort segregated into one of two distinct clusters defined by autoantibodies against Sm/anti-RNP or Ro/La autoantigens, proteins often involved in RNA binding activities. The Sm/RNP cluster was associated with a higher prevalence of serositis in comparison to the Ro/La cluster (P = 0.0022). However, from the available clinical information, no other clinical characteristics were associated with either cluster. In contrast, evaluation of autoantibodies on an individual basis revealed an association between anti-Sm (P = 0.006), RNP-A (P = 0.018) and RNP-70k (P = 0.010) autoantibodies and mucocutaneous symptoms and between anti-RNP-70k and musculoskeletal manifestations (P = 0.059). Serologically active, but clinically quiescent disease also had a higher prevalence of anti-IFN-α autoantibodies. Based on our findings that most SLE patients belong to either a Sm/RNP or Ro/La autoantigen cluster, these results suggest the possibility that alterations in RNA-RNA-binding protein interactions may play a critical role in triggering and/or the pathogenesis of SLE.

Project description:BackgroundEpidemiologic data suggest that patients with systemic lupus erythematosus (SLE) have a lower risk of breast cancer than women in the general population. In light of mechanistic studies suggesting that anti-DNA antibodies have anti-cancer effects, we sought to examine breast cancer risk in autoantibody strata in a well-characterized SLE cohort.MethodsSLE patients without a cancer diagnosis prior to entry in the Hopkins Lupus Cohort were studied (N = 2431). Overall and site-specific cancer incidence was calculated in racial strata and compared with the US Surveillance, Epidemiology and End Results (SEER) registry. Breast cancer incidence was further examined in autoantibody subsets. Patients were considered positive for an autoantibody if they were ever positive for a specificity during their disease course.ResultsPatients with SLE had a 37% lower risk of breast cancer (SIR 0.63, 95% CI 0.39-0.95). The risk of HPV-associated cancers (SIR 4.39, 95% CI 2.87-6.44) and thyroid cancer (SIR 2.27, 95% CI 1.04-4.30) was increased. Cancer risk varied by race, with breast cancer protection occurring in non-African Americans (SIR 0.29, 95% CI 0.11-0.63) and the increased risk of HPV-associated cancers occurring in African Americans (SIR 7.23, 95% CI 4.35-11.3). Breast cancer risk was decreased in patients ever positive for anti-dsDNA (SIR 0.55, 95% CI 0.29-0.96), anti-La (SIR 0.00, 95% CI 0.00-0.78), and lupus anticoagulant (SIR 0.37, 95% CI 0.10-0.94). Patients who were positive for fewer (0-2) SLE autoantibodies did not have a lower risk of breast cancer (SIR 0.84, 95% CI 0.47-1.39), but patients with 3+ autoantibodies had a 59% decreased risk (SIR 0.41, 95% CI 0.16-0.84).ConclusionsPositivity for multiple SLE autoantibodies was associated with a lower risk of breast cancer, supporting the hypothesis that a highly diversified immune response may exert an anti-cancer effect against some cancers. Validation of racial differences in cancer risk in SLE is required to determine whether cancer screening strategies should be targeted to racial subgroups.

Dataset Information

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

Objectives

Methods

Results

Conclusion

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets