Emerging Technologies in the management of the systemic lupus erythematosus (SLE)

Systemic lupus erythematosus (SLE)?is a complex multi-organ autoimmune disease, marked by a huge bio-clinical polymorphism and a large course heterogeneity making the diagnosis, the treatment, and the prognosis too difficult to assess.

Until recently has not seen the necessary paradigm shifts in treatment options to facilitate optimal care. Recent updates to management guidelines, greater understanding of best clinical practices (including steroid-sparing and optimal use of hydroxychloroquine), and the advent of new treatment options offer renewed hope for better patient outcomes in SLE.

Improving understanding of best practice in SLE is therefore of paramount importance in supporting the development of multidisciplinary knowledge among physicians worldwide.

The emerging technologies with data science and artificial intelligence (AI) are recently used to help both healthcare professionals and patients to have the best possible knowledge about the disease so that the most efficient and the safest therapies can be used at the most convenient time to improve the disease prognosis and the quality of life of the patients.

A recent study, published on 14 April 2022 in Frontiers in Genetics (Jiang Z, Shao M, Dai X, Pan Z, Liu D. Identification of Diagnostic Biomarkers in Systemic Lupus Erythematosus Based on Bioinformatics Analysis and Machine Learning.?Front Genet. 2022;13:865559. Published 2022 Apr 14. doi:10.3389/fgene.2022.86555) ?was exploring new insights on genetic factors that may help reveal SLE etiology and improve the survival of SLE patients through the use of bioinformatics analysis and Machine Learning. It is designed to identify key genes involved in SLE and develop potential diagnostic biomarkers for SLE in clinical practice.

Ten potential diagnostic SLE biomarkers (IFI44, IFI44L, EIF2AK2, IFIT3, IFITM3, ZBP1, TRIM22, and PRIC285) were found by integrating bioinformatics methods. Five learning algorithms have discovered that IFI44 can be considered as an optimal biomarker for SLE. The quantitative real-time PCR (qRT-PCR) and Receiver operating characteristic (ROC) curve analysis were performed to validate the diagnostic performance of IFI44 in an independent cohort. Immune cell infiltration showed the proportion of central memory CD8+ T cells was significantly high and positively correlated with selected biomarkers in SLE patients. The construction of the miRNA-diagnostic biomarker-TF regulatory network and drug-gene network provides ideas for further exploring the pathogenesis at the genetic level and treatment of SLE.

Another study published in January 2022 in ACR Open Rheumatology (Diaz-Gallo LM, Oke V, Lundstr?m E, et al. Four Systemic Lupus Erythematosus Subgroups, Defined by Autoantibodies Status, Differ Regarding HLA-DRB1 Genotype Associations and Immunological and Clinical Manifestations.?ACR Open Rheumatol. 2022;4(1):27-39. doi:10.1002/acr2.11343) demonstrates, ?that a subdivision of patients with SLE into four subgroups, based on the profile of 13 commonly measured SLE-related autoantibodies, reveals differences across the groups regarding genetic background, age of disease onset, cytokine profile, clinical manifestations, disease activity, and organ damage characteristics. During this study, researchers have performed an unsupervised cluster analysis based on the detection of 13 SLE-associated autoantibodies (double-stranded DNA, nucleosomes, ribosomal P, ribonucleoprotein [RNP] 68, RNPA, Smith [Sm], Sm/RNP, Sj?gren’s syndrome antigen A [SSA]/Ro52, SSA/Ro60, Sj?gren’s syndrome antigen B [SSB]/La, cardiolipin [CL] Immunoglobulin G [IgG], CL–Immunoglobulin M [IgM], and β2 glycoprotein I [β2GPI]–IgG) in 911 patients with SLE of two cohorts from three Swedish and two United States centers.

The authors conclude by: ” These groups differ regarding genetic predisposition as well as clinical and laboratory characteristics. Replication studies in other genetic ancestries, with a longitudinal design, including incident cases, evaluating additional relevant data domains (eg, all known SLE genetic risk factors and relevant tissue and cell transcriptomics) are necessary before our results can be used in a clinical context. Still the current results are important, in line with previous studies and clinical experience, and they may influence future delineations and treatment decisions for patients with SLE”.

A similar study using Long-term Autoantibody Data and Artificial Intelligence (AI) has identified 4 Lupus Subgroups Associated with Lupus Outcomes

?A group of 805 people newly diagnosed with lupus were examined. Their demographic, clinical, and blood were analyzed for five years.

The analysis revealed four autoantibody profiles of lupus outcomes:

1. Cluster 1 – Identified by the biomarkers anti-Sm and anti-RNP – typically youngest at disease onset and of Asian or African ancestry. At year 5, this group had the highest disease activity and most likely to be on immunosuppressive therapy.
2. Cluster 2 – Low frequency of anti-dsDNA and high anti-DFS70 – typically oldest at disease onset. At year 5, this group had the lowest disease activity and least likely to have kidney disease and to be on immunosuppressive medications.
3. Cluster 3 – High frequency of antiphospholipid antibodies – typically of European ancestry, elevated body mass index. At year 5, most likely to have kidney disease and neuropsychiatric involvement that included strokes and seizures.
4. Cluster 4 – High frequency of anti-SSA/Ro60, anti-SSB/La, anti-Ro52/TIM21, anti-ribosomal P, anti-dsDNA anti-histone – At year 5, exhibited low complements (proteins that protect the body against infections)

?(https://www.lupus.org/news/researchers-identify-four-lupus-subgroups-associated-with-lupus-outcomes-using-longterm).

A promising study published as an abstract entitled “ Machine Learning: Identifying Lupus Nephritis Within Systemic Lupus Erythematosus in the Real World in ACR Convergence 2021, aimed to develop a machine learning (ML)-based approach to classify SLE patients at high risk of LN to assist rheumatologists in their diagnosis.

(https://acrabstracts.org/abstract/machine-learning-identifying-lupus-nephritis-within-systemic-lupus-erythematosus-in-the-real-world/)

“After testing 2,520 models using the 6 most commonly used classification algorithms we found that the penalized logistic regression (PLR) with elastic net regularization predicted which SLE patients were at highest risk of LN (AUC: 0.91, with negative/positive predictive values of 0.96 and 0.68, respectively) in the testing set. The 3 variables that best predicted LN risk were disease progression, skin problems (both contributing negatively to risk), and musculoskeletal organs affected at diagnosis (with a positive contribution to risk,

PLR successfully predicted SLE patients’ LN risk using real-world data. Although linear discriminant analysis had a slightly better AUC (0.92), PLR results are easier to interpret, making it a suitable model to support rheumatologists in identifying LN patients within the SLE population to guide further testing and treatment.

The PLR model had better discriminative power in non-LN vs LN patients. This may have resulted from undiagnosed LN patients remaining within the non-LN patient pool and thus generating false positives, since these high LN risk non-LN patients shared a number of characteristics with LN patients.

Predictive analysis has shown promising results for LN risk assessment in SLE patients using real-world data, we recommend further prospective validation is required prior to use in a clinical setting”.

?

We see here that data science and AI are taking more and more place in the SLE biomedical research with the development of new techniques and the findings of new biomarkers that can offer great opportunities to improve the management of a difficult and complex systemic disease.

The adoption of emerging technologies is also exponentially increasing in the research on other rheumatic diseases. The collaboration between Technology experts, biomedical researchers, and healthcare professionals is crucial for the success of this approach.