Genomic risk scores for juvenile idiopathic arthritis and its subtypes

Machine learning and artificial intelligence within pediatric autoimmune diseases: applications, challenges, future perspective

INTRODUCTION

Autoimmune disorders affect 4.5% to 9.4% of children, significantly reducing their quality of life. The diagnosis and prognosis of autoimmune diseases are uncertain because of the variety of onset and development. Machine learning can identify clinically relevant patterns from vast amounts of data. Hence, its introduction has been beneficial in the diagnosis and management of patients.

AREAS COVERED

This narrative review was conducted through searching various electronic databases, including PubMed, Scopus, and Web of Science. This study thoroughly explores the current knowledge and identifies the remaining gaps in the applications of machine learning specifically in the context of pediatric autoimmune and related diseases.

EXPERT OPINION

Machine learning algorithms have the potential to completely change how pediatric autoimmune disorders are identified, treated, and managed. Machine learning can assist physicians in making more precise and fast judgments, identifying new biomarkers and therapeutic targets, and personalizing treatment strategies for each patient by utilizing massive datasets and powerful analytics.

Genome Sequencing in an Individual Presenting with 22q11.2 Deletion Syndrome and Juvenile Idiopathic Arthritis

Juvenile idiopathic arthritis is a heterogeneous group of diseases characterized by arthritis with poorly known causes, including monogenic disorders and multifactorial etiology. 22q11.2 proximal deletion syndrome is a multisystemic disease with over 180 manifestations already described. In this report, the authors describe a patient presenting with a short stature, neurodevelopmental delay, and dysmorphisms, who had an episode of polyarticular arthritis at the age of three years and eight months, resulting in severe joint limitations, and was later diagnosed with 22q11.2 deletion syndrome. Investigation through Whole Genome Sequencing revealed that he had no pathogenic or likely-pathogenic variants in both alleles of the MIF gene or in genes associated with monogenic arthritis (LACC1, LPIN2, MAFB, NFIL3, NOD2, PRG4, PRF1, STX11, TNFAIP3, TRHR, UNC13DI). However, the patient presented 41 risk polymorphisms for juvenile idiopathic arthritis. Thus, in the present case, arthritis seems coincidental to 22q11.2 deletion syndrome, probably caused by a multifactorial etiology. The association of the MIF gene in individuals previously described with juvenile idiopathic arthritis and 22q11.2 deletion seems unlikely since it is located in the distal and less-frequently deleted region of 22q11.2 deletion syndrome.

Advancements and progress in juvenile idiopathic arthritis: A Review of pathophysiology and treatment

Juvenile idiopathic arthritis (JIA) is a chronic clinical condition characterized by arthritic features in children under the age of 16, with at least 6 weeks of active symptoms. The etiology of JIA remains unknown, and it is associated with prolonged synovial inflammation and structural joint damage influenced by environmental and genetic factors. This review aims to enhance the understanding of JIA by comprehensively analyzing relevant literature. The focus lies on current diagnostic and therapeutic approaches and investigations into the pathoaetiologies using diverse research modalities, including in vivo animal models and large-scale genome-wide studies. We aim to elucidate the multifactorial nature of JIA with a strong focus towards genetic predilection, while proposing potential strategies to improve therapeutic outcomes and enhance diagnostic risk stratification in light of recent advancements. This review underscores the need for further research due to the idiopathic nature of JIA, its heterogeneous phenotype, and the challenges associated with biomarkers and diagnostic criteria. Ultimately, this contribution seeks to advance the knowledge and promote effective management strategies in JIA.

Genomic Machine Learning Meta-regression: Insights on Associations of Study Features With Reported Model Performance

Many studies have been conducted with the goal of correctly predicting diagnostic status of a disorder using the combination of genomic data and machine learning. It is often hard to judge which components of a study led to better results and whether better reported results represent a true improvement or an uncorrected bias inflating performance. We extracted information about the methods used and other differentiating features in genomic machine learning models. We used these features in linear regressions predicting model performance. We tested for univariate and multivariate associations as well as interactions between features. Of the models reviewed, 46% used feature selection methods that can lead to data leakage. Across our models, the number of hyperparameter optimizations reported, data leakage due to feature selection, model type, and modeling an autoimmune disorder were significantly associated with an increase in reported model performance. We found a significant, negative interaction between data leakage and training size. Our results suggest that methods susceptible to data leakage are prevalent among genomic machine learning research, resulting in inflated reported performance. Best practice guidelines that promote the avoidance and recognition of data leakage may help the field avoid biased results.

The Application of Genetic Risk Scores in Rheumatic Diseases: A Perspective

Modest effect sizes have limited the clinical applicability of genetic associations with rheumatic diseases. Genetic risk scores (GRSs) have emerged as a promising solution to translate genetics into useful tools. In this review, we provide an overview of the recent literature on GRSs in rheumatic diseases. We describe six categories for which GRSs are used: (a) disease (outcome) prediction, (b) genetic commonalities between diseases, (c) disease differentiation, (d) interplay between genetics and environmental factors, (e) heritability and transferability, and (f) detecting causal relationships between traits. In our review of the literature, we identified current lacunas and opportunities for future work. First, the shortage of non-European genetic data restricts the application of many GRSs to European populations. Next, many GRSs are tested in settings enriched for cases that limit the transferability to real life. If intended for clinical application, GRSs are ideally tested in the relevant setting. Finally, there is much to elucidate regarding the co-occurrence of clinical traits to identify shared causal paths and elucidate relationships between the diseases. GRSs are useful instruments for this. Overall, the ever-continuing research on GRSs gives a hopeful outlook into the future of GRSs and indicates significant progress in their potential applications.

A compendium of mitochondrial molecular characteristics provides novel perspectives on the treatment of rheumatoid arthritis patients

Rheumatoid arthritis (RA) is an autoimmune disease that exhibits a high degree of heterogeneity, marked by unpredictable disease flares and significant variations in the response to available treatments. The lack of optimal stratification for RA patients may be a contributing factor to the poor efficacy of current treatment options. The objective of this study is to elucidate the molecular characteristics of RA through the utilization of mitochondrial genes and subsequently construct and authenticate a diagnostic framework for RA. Mitochondrial proteins were obtained from the MitoCarta database, and the R package limma was employed to filter for differentially expressed mitochondrial genes (MDEGs). Metascape was utilized to perform enrichment analysis, followed by an unsupervised clustering algorithm using the ConsensuClusterPlus package to identify distinct subtypes based on MDEGs. The immune microenvironment, biological pathways, and drug response were further explored in these subtypes. Finally, a multi-biomarker-based diagnostic model was constructed using machine learning algorithms. Utilizing 88 MDEGs present in transcript profiles, it was possible to classify RA patients into three distinct subtypes, each characterized by unique molecular and cellular signatures. Subtype A exhibited a marked activation of inflammatory cells and pathways, while subtype C was characterized by the presence of specific innate lymphocytes. Inflammatory and immune cells in subtype B displayed a more modest level of activation (Wilcoxon test P < 0.05). Notably, subtype C demonstrated a stronger correlation with a superior response to biologics such as infliximab, anti-TNF, rituximab, and methotrexate/abatacept (P = 0.001) using the fisher test. Furthermore, the mitochondrial diagnosis SVM model demonstrated a high degree of discriminatory ability in distinguishing RA in both training (AUC = 100%) and validation sets (AUC = 80.1%). This study presents a pioneering analysis of mitochondrial modifications in RA, offering a novel framework for patient stratification and potentially enhancing therapeutic decision-making.

Understanding the role and adoption of artificial intelligence techniques in rheumatology research: An in-depth review of the literature

The major and upward trend in the number of published research related to rheumatic and musculoskeletal diseases, in which artificial intelligence plays a key role, has exhibited the interest of rheumatology researchers in using these techniques to answer their research questions. In this review, we analyse the original research articles that combine both worlds in a five- year period (2017-2021). In contrast to other published papers on the same topic, we first studied the review and recommendation articles that were published during that period, including up to October 2022, as well as the publication trends. Secondly, we review the published research articles and classify them into one of the following categories: disease identification and prediction, disease classification, patient stratification and disease subtype identification, disease progression and activity, treatment response, and predictors of outcomes. Thirdly, we provide a table with illustrative studies in which artificial intelligence techniques have played a central role in more than twenty rheumatic and musculoskeletal diseases. Finally, the findings of the research articles, in terms of disease and/or data science techniques employed, are highlighted in a discussion. Therefore, the present review aims to characterise how researchers are applying data science techniques in the rheumatology medical field. The most immediate conclusions that can be drawn from this work are: multiple and novel data science techniques have been used in a wide range of rheumatic and musculoskeletal diseases including rare diseases; the sample size and the data type used are heterogeneous, and new technical approaches are expected to arrive in the short-middle term.

Study of the shared gene signatures of polyarticular juvenile idiopathic arthritis and autoimmune uveitis

Objective

To explore the shared gene signatures and potential molecular mechanisms of polyarticular juvenile idiopathic arthritis (pJIA) and autoimmune uveitis (AU).

Method

The microarray data of pJIA and AU from the Gene Expression Omnibus (GEO) database were downloaded and analyzed. The GEO2R tool was used to identify the shared differentially expressed genes (DEGs) and genes of extracellular proteins were identified among them. Then, weighted gene co-expression network analysis (WGCNA) was used to identify the shared immune-related genes (IRGs) related to pJIA and AU. Moreover, the shared transcription factors (TFs) and microRNAs (miRNAs) in pJIA and AU were acquired by comparing data from HumanTFDB, hTFtarget, GTRD, HMDD, and miRTarBase. Finally, Metascape and g: Profiler were used to carry out function enrichment analyses of previously identified gene sets.

Results

We found 40 up-regulated and 15 down-regulated shared DEGs via GEO2R. Then 24 shared IRGs in positivity-related modules, and 18 shared IRGs in negatively-related modules were found after WGCNA. After that, 3 shared TFs (ARID1A, SMARCC2, SON) were screened. And the constructed TFs-shared DEGs network indicates a central role of ARID1A. Furthermore, hsa-miR-146 was found important in both diseases. The gene sets enrichment analyses suggested up-regulated shared DEGs, TFs targeted shared DEGs, and IRGs positivity-correlated with both diseases mainly enriched in neutrophil degranulation process, IL-4, IL-13, and cytokine signaling pathways. The IRGs negatively correlated with pJIA and AU mainly influence functions of the natural killer cell, cytotoxicity, and glomerular mesangial cell proliferation. The down-regulated shared DEGs and TFs targeted shared DEGs did not show particular functional enrichment.

Conclusion

Our study fully demonstrated the flexibility and complexity of the immune system disorders involved in pJIA and AU. Neutrophil degranulation may be considered the shared pathogenic mechanism, and the roles of ARID1A and MiR-146a are worthy of further in-depth study. Other than that, the importance of periodic inspection of kidney function is also noteworthy.

Juvenile idiopathic arthritis polygenic risk scores are associated with cardiovascular phenotypes in early adulthood: a phenome-wide association study

BACKGROUND

There is growing concern about the long-term cardiovascular health of patients with juvenile idiopathic arthritis (JIA). In this study we assessed the association between JIA polygenic risk and cardiovascular phenotypes (cardiovascular risk factors, early atherosclerosis/arteriosclerosis markers, and cardiac structure and function measures) early in life.

METHODS

JIA polygenic risk scores (PRSs) were constructed for 2,815 participants from the Avon Longitudinal Study of Parents and Children, using the single nucleotide polymorphism (SNP) weights from the most recent JIA genome wide association study. The association between JIA PRSs and cardiovascular phenotypes at age 24 years was assessed using linear and logistic regression. For outcomes with strong evidence of association, further analysis was undertaken to examine how early in life (from age seven onwards) these associations manifest.

RESULTS

The JIA PRS was associated with diastolic blood pressure (β 0.062, 95% CI 0.026 to 0.099, P = 0.001), insulin (β 0.050, 95% CI 0.011 to 0.090, P = 0.013), insulin resistance index (HOMA2_IR, β 0.054, 95% CI 0.014 to 0.095, P = 0.009), log hsCRP (β 0.053, 95% CI 0.011 to 0.095, P = 0.014), waist circumference (β 0.041, 95% CI 0.007 to 0.075, P = 0.017), fat mass index (β 0.049, 95% CI 0.016 to 0.083, P = 0.004) and body mass index (β 0.046, 95% CI 0.011 to 0.081, P = 0.010). For anthropometric measures and diastolic blood pressure, there was suggestive evidence of association with JIA PRS from age seven years. The findings were consistent across multiple sensitivity analyses.

CONCLUSIONS

Genetic liability to JIA is associated with multiple cardiovascular risk factors, supporting the hypothesis of increased cardiovascular risk in JIA. Our findings suggest that cardiovascular risk is a core feature of JIA, rather than secondary to the disease activity/treatment, and that cardiovascular risk counselling should form part of patient care.

Responsible use of polygenic risk scores in the clinic: potential benefits, risks and gaps

Polygenic risk scores (PRSs) aggregate the many small effects of alleles across the human genome to estimate the risk of a disease or disease-related trait for an individual. The potential benefits of PRSs include cost-effective enhancement of primary disease prevention, more refined diagnoses and improved precision when prescribing medicines. However, these must be weighed against the potential risks, such as uncertainties and biases in PRS performance, as well as potential misunderstanding and misuse of these within medical practice and in wider society. By addressing key issues including gaps in best practices, risk communication and regulatory frameworks, PRSs can be used responsibly to improve human health. Here, the International Common Disease Alliance's PRS Task Force, a multidisciplinary group comprising expertise in genetics, law, ethics, behavioral science and more, highlights recent research to provide a comprehensive summary of the state of polygenic score research, as well as the needs and challenges as PRSs move closer to widespread use in the clinic.

Precision medicine in juvenile idiopathic arthritis-has the time arrived?

The introduction of disease-modifying anti-rheumatic drug therapies for treating children and adolescents with chronic arthritis (ie, juvenile idiopathic arthritis [JIA]) has revolutionised care and outcomes. The biologic revolution continues to expand, with ever-changing immunological targets coming to market after basic research and clinical trials. The first class of biologics that was beneficial for children with JIA was tumour necrosis factor (TNF) inhibitors. If used early and aggressively, TNF inhibitors are capable of inducing disease remission for most of the seven subtypes of JIA, with the exception of systemic JIA (which more frequently responds to interleukin [IL]-1 or IL-6 inhibition). Nevertheless, there are still subsets of patients with JIA with disease that is difficult to treat or who develop extra-articular features that require a different therapeutic approach. Although finding an effective biological therapy for individual children with JIA can be trial and error, ongoing research and clinical trials are providing insight into a more personalised approach to care. In addition, redefining the JIA classification, in part based on shared similarities with various adult arthritides, could allow for extrapolation of knowledge from studies in adults with chronic arthritis.