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

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.

Different Immunologic Profiles Are Associated With Distinct Clinical Phenotypes in Longitudinally Observed Patients With Systemic Lupus Erythematosus

“…Recently, clustering of patients based on their autoantibody profile identified a cluster with high levels of anti-SM and -RNP antibodies that had high cumulative disease activity, more mucocutaneous disease, and a higher proportion of patients with African as compared to European or Hispanic ancestry. 35 Given the similarity of these clinical and demographic features to those seen in cluster 1, this is likely the same subset of patients.…”

“…Notably, we show that patients with persistent B cell activation and ABC expansion are more likely to have prior disease activity, ongoing disease activity, and/or subsequent flares, suggesting that the failure to attenuate this B cell activation following treatment is associated with an increased propensity to develop a flare. Recently, clustering of patients based on their autoantibody profile identified a cluster with high levels of anti‐SM and ‐RNP antibodies that had high cumulative disease activity, more mucocutaneous disease, and a higher proportion of patients with African as compared to European or Hispanic ancestry 35 . Given the similarity of these clinical and demographic features to those seen in cluster 1, this is likely the same subset of patients.…”

Application of digital health technology in autoimmune diseases: Opportunity and challenge

“…5 In a multinational cohort study on systemic lupus erythematosus, machine learning was employed to predict long-term disease activity, organ involvement, treatment requirements, and mortality risk. 6 By integrating diverse data sources, such as clinical data, genetic information, and biomarkers, digital health technology helps unveil the intricate mechanisms of diseases, providing comprehensive information support for personalized treatment decisions.…”

“…For instance, AI, as an integral component of digital healthcare, utilizes techniques such as deep learning and pattern recognition to effectively handle vast medical datasets, including imaging, genetic sequencing, and laboratory results, thereby aiding rheumatologists in the expedited identification of autoimmune diseases 5 . In a multinational cohort study on systemic lupus erythematosus, machine learning was employed to predict long‐term disease activity, organ involvement, treatment requirements, and mortality risk 6 …”

Prediction of Treatment Effect of SLE-ITP Patients Based on Cost-Sensitive Neural Network and Variational Autoencoder

“…For instance, a recent study implemented AI to distinguish systemic lupus erythematosus and primary Sjögren syndrome using gene expression and methylation data from 651 individuals, and analyzed the impact of the heterogeneity of these diseases on the performance of predictive models. 21 However, the reliability of AI models is highly correlated with the quality of the data, and the decision-making process of most models is difficult to interpret, which may challenge interpretability requirements in biological research and clinical applications. 22 In this study, we retrieved 324 samples of patients with lupus and thrombocytopenia from the electronic health record database, including blood routine, blood lymphocytes, biochemical, antibody, complement, and other laboratory test indicators.…”