Biomarkers of erosive arthritis in systemic lupus erythematosus: Application of machine learning models

Rough hypervolume-driven feature selection with groupwise intelligent sampling for detecting clinical characterization of lupus nephritis

Systemic lupus erythematosus (SLE) is an autoimmune inflammatory disease. Lupus nephritis (LN) is a major risk factor for morbidity and mortality in SLE. Proliferative and pure membranous LN have different prognoses and may require different treatments. This study proposes a binary rough hypervolume-driven spherical evolution algorithm with groupwise intelligent sampling (bRGSE). The efficient dimensionality reduction capability of the bRGSE is verified across twelve datasets. These datasets are from the public datasets, with feature dimensions ranging from seven hundred to fifty thousand. The experimental results indicate that bRGSE performs better than seven high-performing alternatives. Then, the bRGSE was combined with adaptive boosting (AdaBoost) to form a new model (bRGSE_AdaBoost), which analyzed clinical records collected from 110 patients with LN. Experimental results show that the proposed bRGSE_AdaBoost can identify the most critical indicators, including urine latent blood, white blood cells, endogenous creatinine clearing rate, and age. These indicators may help differentiate between proliferative LN and membranous LN. The proposed bRGSE algorithm is an efficient dimensionality reduction method. The developed bRGSE_AdaBoost model, a computer-aided model, achieved an accuracy of 96.687 % and is expected to provide early warning for the treatment and diagnosis of LN.

Examining the clinical and radiological landscape of rhupus: navigating the challenges in disease classification

Rhupus, in the broad sense, refers to an overlap between rheumatoid arthritis (RA) and lupus. However, there is a paucity of data on the appropriate diagnostic/classification criteria that should be used to define rhupus. Hence, we undertook this narrative review to analyze the clinical characteristics, radiology, and treatment with a focus on diagnostic challenges and defining features of rhupus. The databases of Medline/PubMed, Scopus, and DOAJ were searched for relevant articles using the following keywords: ("Rhupus"), ("lupus" AND "erosive" AND "arthritis"), and ("lupus" AND "rheumatoid arthritis" AND "overlap"). Studies have used a variety of classification criteria for rhupus of which a combination of the latest classification criteria for RA and lupus along with positive anti-cyclic citrullinated peptide, anti-Smith, and anti-dsDNA antibodies seem most relevant. The majority of rhupus cohorts report the onset of the disease as RA (two-thirds of rhupus patients) followed by the development of features of lupus at an average interval of 3-11.3 years. The radiographic features and distribution of erosions are similar to RA. However, ultrasonography and MRI reveal erosions in pure lupus related arthritis as well. This makes the reliability of radiologic tools for the evaluation of rhupus supportive at the most. Extra-articular features in rhupus are mild with major organ involvement in the form of neuropsychiatric lupus and lupus nephritis being rare. We have further discussed the fallacies of the various classification criteria and proposed a theme for classifying rhupus which needs to be tested and validated in future studies. Our current state of understanding supports rhupus as an overlap of SLE and RA with articular disease similar to RA with the extra-articular disease being milder than SLE. Developing standardized classification criteria for rhupus will help in the early diagnosis and prevention of articular damage in patients with rhupus.

Systemic lupus in the era of machine learning medicine

Artificial intelligence and machine learning applications are emerging as transformative technologies in medicine. With greater access to a diverse range of big datasets, researchers are turning to these powerful techniques for data analysis. Machine learning can reveal patterns and interactions between variables in large and complex datasets more accurately and efficiently than traditional statistical methods. Machine learning approaches open new possibilities for studying SLE, a multifactorial, highly heterogeneous and complex disease. Here, we discuss how machine learning methods are rapidly being integrated into the field of SLE research. Recent reports have focused on building prediction models and/or identifying novel biomarkers using both supervised and unsupervised techniques for understanding disease pathogenesis, early diagnosis and prognosis of disease. In this review, we will provide an overview of machine learning techniques to discuss current gaps, challenges and opportunities for SLE studies. External validation of most prediction models is still needed before clinical adoption. Utilisation of deep learning models, access to alternative sources of health data and increased awareness of the ethics, governance and regulations surrounding the use of artificial intelligence in medicine will help propel this exciting field forward.

How AI May Transform Musculoskeletal Imaging

While musculoskeletal imaging volumes are increasing, there is a relative shortage of subspecialized musculoskeletal radiologists to interpret the studies. Will artificial intelligence (AI) be the solution? For AI to be the solution, the wide implementation of AI-supported data acquisition methods in clinical practice requires establishing trusted and reliable results. This implementation will demand close collaboration between core AI researchers and clinical radiologists. Upon successful clinical implementation, a wide variety of AI-based tools can improve the musculoskeletal radiologist's workflow by triaging imaging examinations, helping with image interpretation, and decreasing the reporting time. Additional AI applications may also be helpful for business, education, and research purposes if successfully integrated into the daily practice of musculoskeletal radiology. The question is not whether AI will replace radiologists, but rather how musculoskeletal radiologists can take advantage of AI to enhance their expert capabilities.

Machine learning: Predicting hospital length of stay in patients admitted for lupus flares

BACKGROUND

Although rare, severe systemic lupus erythematosus (SLE) flares requiring hospitalization account for most of the direct costs of SLE care. New machine learning (ML) methods may optimize lupus care by predicting which patients will have a prolonged hospital length of stay (LOS). Our study uses a machine learning approach to predict the LOS in patients admitted for lupus flares and assesses which features prolong LOS.

METHODS

Our study sampled 5831 patients admitted for lupus flares from the National Inpatient Sample Database 2016-2018 and collected 90 demographics and comorbidity features. Four machine learning (ML) models were built (XGBoost, Linear Support Vector Machines, K Nearest Neighbors, and Logistic Regression) to predict LOS, and their performance was evaluated using multiple metrics, including accuracy, receiver operator area under the curve (ROC-AUC), precision-recall area under the curve (PR- AUC), and F1-score. Using the highest-performing model (XGBoost), we assessed the feature importance of our input features using Shapley value explanations (SHAP) to rank their impact on LOS.

RESULTS

Our XGB model performed the best with a ROC-AUC of 0.87, PR-AUC of 0.61, an F1 score of 0.56, and an accuracy of 95%. The features with the most significant impact on the model were "the need for a central line," "acute dialysis," and "acute renal failure." Other top features include those related to renal and infectious comorbidities.

CONCLUSION

Our results were consistent with the established literature and showed promise in ML over traditional methods of predictive analyses, even with rare rheumatic events such as lupus flare hospitalizations.

Artificial Intelligence and laboratory data in rheumatic diseases

Artificial intelligence (AI)-based medical technologies are rapidly evolving into actionable solutions for clinical practice. Machine learning (ML) algorithms can process increasing amounts of laboratory data such as gene expression immunophenotyping data and biomarkers. In recent years, the analysis of ML has become particularly useful for the study of complex chronic diseases, such as rheumatic diseases, heterogenous conditions with multiple triggers. Numerous studies have used ML to classify patients and improve diagnosis, to stratify the risk and determine disease subtypes, as well as to discover biomarkers and gene signatures. This review aims to provide examples of ML models for specific rheumatic diseases using laboratory data and some insights into relevant strengths and limitations. A better understanding and future application of these analytical strategies could facilitate the development of precision medicine for rheumatic patients.

Artificial intelligence and high-dimensional technologies in the theragnosis of systemic lupus erythematosus

Systemic lupus erythematosus is a complex, systemic autoimmune disease characterised by immune dysregulation. Pathogenesis is multifactorial, contributing to clinical heterogeneity and posing challenges for diagnosis and treatment. Although strides in treatment options have been made in the past 15 years, with the US Food and Drug Administration approval of belimumab in 2011, there are still many patients who have inadequate responses to therapy. A better understanding of underlying disease mechanisms with a holistic and multiparametric approach is required to improve clinical assessment and treatment. This Review discusses the evolution of genomics, epigenomics, transcriptomics, and proteomics in the study of systemic lupus erythematosus and ways to amalgamate these silos of data with a systems-based approach while also discussing ways to strengthen the overall process. These mechanistic insights will facilitate the discovery of functionally relevant biomarkers to guide rational therapeutic selection to improve patient outcomes.

Application of Machine Learning Models in Systemic Lupus Erythematosus

Systemic Lupus Erythematosus (SLE) is a systemic autoimmune disease and is extremely heterogeneous in terms of immunological features and clinical manifestations. This complexity could result in a delay in the diagnosis and treatment introduction, with impacts on long-term outcomes. In this view, the application of innovative tools, such as machine learning models (MLMs), could be useful. Thus, the purpose of the present review is to provide the reader with information about the possible application of artificial intelligence in SLE patients from a medical perspective. To summarize, several studies have applied MLMs in large cohorts in different disease-related fields. In particular, the majority of studies focused on diagnosis and pathogenesis, disease-related manifestations, in particular Lupus Nephritis, outcomes and treatment. Nonetheless, some studies focused on peculiar features, such as pregnancy and quality of life. The review of published data demonstrated the proposal of several models with good performance, suggesting the possible application of MLMs in the SLE scenario.

Current state and completeness of reporting clinical prediction models using machine learning in systemic lupus erythematosus: A systematic review

OBJECTIVE

We carried out a systematic review (SR) of adherence in diagnostic and prognostic applications of ML in SLE using the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) Statement.

METHODS

A SR employing five databases was conducted from its inception until December 2021. We identified articles that evaluated the utilization of ML for prognostic and/or diagnostic purposes. This SR was reported based on the PRISMA guidelines. The TRIPOD statement assessed adherence to reporting standards. Assessment for risk of bias was done using PROBAST tool.

RESULTS

We included 45 studies: 29 (64.4%) diagnostic and 16 (35.5%) prognostic prediction- model studies. Overall, articles adhered by between 17% and 67% (median 43%, IQR 37-49%) to TRIPOD items. Only few articles reported the model's predictive performance (2.3%, 95% CI 0.06-12.0), testing of interaction terms (2.3%, 95% CI 0.06-12.0), flow of participants (50%, 95% CI; 34.6-65.4), blinding of predictors (2.3%, 95% CI 0.06-12.0), handling of missing data (36.4%, 95% CI 22.4-52.2), and appropriate title (20.5%, 95% CI 9.8-35.3). Some items were almost completely reported: the source of data (88.6%, 95% CI 75.4-96.2), eligibility criteria (86.4%, 95% CI 76.2-96.5), and interpretation of findings (88.6%, 95% CI 75.4-96.2). In addition, most of model studies had high risk of bias.

CONCLUSIONS

The reporting adherence of ML-based model developed for SLE, is currently inadequate. Several items deemed crucial for transparent reporting were not fully reported in studies on ML-based prediction models.

REVIEW REGISTRATION

PROSPERO ID# CRD42021284881. (Amended to limit the scope).

Anti-Carbamylated Protein (Anti-CarP) Antibodies in Patients Evaluated for Suspected Rheumatoid Arthritis

(1) Background: Anti-carbamylated protein (CarP) antibodies have been studied as novel markers to aid in the diagnosis and prognosis of rheumatoid arthritis. (2) Methods: A total of 265 samples were included in the evaluation, for which 98 had results for anti-cyclic citrullinated peptide (CCP), 86 for rheumatoid factor (RF), and 212 for 14-3-3 eta protein. Anti-CarP antibodies were measured using a fetal calf serum-based single-step assay (research use only, Inova Diagnostics, San Diego, CA). (3) Results: Anti-CarP antibodies were significantly higher and more frequent in anti-CCP3.1+ (p = 0.0025), RF+ (p = 0.0043) and 14-3-3 eta+ (p = 0.028) samples compared to the negative counterpart group. In addition, isolated anti-CarP positivity occurred in samples negative for anti-CCP3.1, RF, or 14-3-3 eta. When anti-CarP antibodies were compared to each of the RF, anti-CCP3.1, and 14-3-3 eta by receiver operating characteristic (ROC) analyses, the area under the curve (AUC) values of 0.71 (RF), 0.68 (anti-CCP3.1), and 0.59 (14-3-3 eta), respectively, demonstrated a moderate correlation. Using an UpSet plot, we determined that 10.6% of the samples with available results for anti-CCP3.1, RF, and anti-CarP showed triple positivity. (4) Conclusions: Anti-carbamylated protein (anti-CarP) antibodies can be detected in anti-CCP, RF and 14-3-3 eta-positive and -negative patients, potentially identifying specific subsets of patients.

Lupus nephritis diagnosis using enhanced moth flame algorithm with support vector machines

Systemic lupus erythematosus is a chronic autoimmune disease that affects the kidney in most patients. Lupus nephritis (LN) is divided into six categories by the International Society of Nephrology/Renal Pathology Society (ISN/RPS). The purpose of this research is to build a framework for discriminating between ISN/RPS pure class V(MLN) and classes III ± V or IV ± V (PLN) using real clinical data. The framework is developed by merging a hybrid stochastic optimizer, moth-flame algorithm (HMFO), with a support vector machine (SVM), dubbed HMFO-SVM. The HMFO is constructed by enhancing the original moth-flame algorithm (MFO) with a bee-foraging learning operator, which guarantees that the algorithm speeds convergence and departs from the local optimum. The HMFO is used to optimize parameters and select features simultaneously for SVM on clinical SLE data. On 23 benchmark tests, the suggested HMFO method is validated. Finally, clinical data from LN patients are analyzed to determine the efficacy of HMFO-SVM over other SVM rivals. The statistical findings indicate that all measures have predictive capabilities and that the suggested HMFO-SVM is more stable for analyzing systemic LN. HMFO-SVM may be used to analyze LN as a feasible computer-assisted technique.

Machine learning approaches for the genomic prediction of rheumatoid arthritis and systemic lupus erythematosus

BACKGROUND

Rheumatoid arthritis (RA) and systemic lupus erythematous (SLE) are autoimmune rheumatic diseases that share a complex genetic background and common clinical features. This study's purpose was to construct machine learning (ML) models for the genomic prediction of RA and SLE.

METHODS

A total of 2,094 patients with RA and 2,190 patients with SLE were enrolled from the Taichung Veterans General Hospital cohort of the Taiwan Precision Medicine Initiative. Genome-wide single nucleotide polymorphism (SNP) data were obtained using Taiwan Biobank version 2 array. The ML methods used were logistic regression (LR), random forest (RF), support vector machine (SVM), gradient tree boosting (GTB), and extreme gradient boosting (XGB). SHapley Additive exPlanation (SHAP) values were calculated to clarify the contribution of each SNPs. Human leukocyte antigen (HLA) imputation was performed using the HLA Genotype Imputation with Attribute Bagging package.

RESULTS

Compared with LR (area under the curve [AUC] = 0.8247), the RF approach (AUC = 0.9844), SVM (AUC = 0.9828), GTB (AUC = 0.9932), and XGB (AUC = 0.9919) exhibited significantly better prediction performance. The top 20 genes by feature importance and SHAP values included HLA class II alleles. We found that imputed HLA-DQA1*05:01, DQB1*0201 and DRB1*0301 were associated with SLE; HLA-DQA1*03:03, DQB1*0401, DRB1*0405 were more frequently observed in patients with RA.

CONCLUSIONS

We established ML methods for genomic prediction of RA and SLE. Genetic variations at HLA-DQA1, HLA-DQB1, and HLA-DRB1 were crucial for differentiating RA from SLE. Future studies are required to verify our results and explore their mechanistic explanation.

An introduction to machine learning and analysis of its use in rheumatic diseases

Machine learning (ML) is a computerized analytical technique that is being increasingly employed in biomedicine. ML often provides an advantage over explicitly programmed strategies in the analysis of multidimensional information by recognizing relationships in the data that were not previously appreciated. As such, the use of ML in rheumatology is increasing, and numerous studies have employed ML to classify patients with rheumatic autoimmune inflammatory diseases (RAIDs) from medical records and imaging, biometric or gene expression data. However, these studies are limited by sample size, the accuracy of sample labelling, and absence of datasets for external validation. In addition, there is potential for ML models to overfit or underfit the data and, thereby, these models might produce results that cannot be replicated in an unrelated dataset. In this Review, we introduce the basic principles of ML and discuss its current strengths and weaknesses in the classification of patients with RAIDs. Moreover, we highlight the successful analysis of the same type of input data (for example, medical records) with different algorithms, illustrating the potential plasticity of this analytical approach. Altogether, a better understanding of ML and the future application of advanced analytical techniques based on this approach, coupled with the increasing availability of biomedical data, may facilitate the development of meaningful precision medicine for patients with RAIDs.

Erosive arthritis in systemic lupus erythematosus: not only Rhupus

Systemic lupus erythematosus (SLE)-related arthritis has been traditionally defined as non-erosive and is therefore considered a minor manifestation requiring a mild treatment. However, the concept of non-erosive arthritis in SLE has been challenged with the advent of sensitive imaging techniques, such as high-resolution ultrasound with power Doppler or magnetic resonance. The application of these new imaging tools has demonstrated that up to 40% of SLE patients with joint involvement can develop erosive damage. Thus, this more aggressive phenotype can be identified not only in patients overlapping with rheumatoid arthritis (RA). This issue has been considered for the first time in the classification criteria proposed by Systemic Lupus International Collaborating Clinics in 2012, in which the old definition of "non-erosive arthritis" was replaced with either synovitis or tenderness in two or more joints with morning stiffness, suggesting the possible presence of an erosive phenotype. Accordingly, the 2019 EULAR/ACR's SLE recommendations advise treatment with immunosuppressant or biological drugs for patients with RA-like moderate arthritis. As a result, several studies have investigated the presence of biomarkers associated with SLE erosive damage. A relevant role seems to be played by the autoantibodies directed against post-translational modified proteins: above all, a significant association has been observed with antibodies directed against citrullinated and carbamylated proteins. Conversely, the rheumatoid factor was not associated with this more aggressive SLE-related arthritis. Nonetheless, some pro-inflammatory factors have been associated with erosive damage in SLE patients. These results suggest new pathogenic mechanisms underlining erosive arthritis, only partially shared with RA. Hence, in the present narrative review, we summarized available data about erosive arthritis in SLE patients, in the light of its impact on therapeutic decisions.

Machine Learning in Rheumatic Diseases

With advances in information technology, the demand for using data science to enhance healthcare and disease management is rapidly increasing. Among these technologies, machine learning (ML) has become ubiquitous and indispensable for solving complex problems in many scientific fields, including medical science. ML allows the development of guidelines and framing of the evaluation system for complex diseases based on massive data. In the analysis of rheumatic diseases, which are chronic and remarkably heterogeneous, ML can be anticipated to be extremely helpful in deciphering and revealing the inherent interrelationships in disease development and progression, which can further enhance the overall understanding of the disease, optimize patients' stratification, calibrate therapeutic strategies, and predict prognosis and outcomes. In this review, the basics of ML, its potential clinical applications in rheumatology, together with its strengths and limitations are summarized.

Coupling of Co-expression Network Analysis and Machine Learning Validation Unearthed Potential Key Genes Involved in Rheumatoid Arthritis

Rheumatoid arthritis (RA) is an incurable disease that afflicts 0.5-1.0% of the global population though it is less threatening at its early stage. Therefore, improved diagnostic efficiency and prognostic outcome are critical for confronting RA. Although machine learning is considered a promising technique in clinical research, its potential in verifying the biological significance of gene was not fully exploited. The performance of a machine learning model depends greatly on the features used for model training; therefore, the effectiveness of prediction might reflect the quality of input features. In the present study, we used weighted gene co-expression network analysis (WGCNA) in conjunction with differentially expressed gene (DEG) analysis to select the key genes that were highly associated with RA phenotypes based on multiple microarray datasets of RA blood samples, after which they were used as features in machine learning model validation. A total of six machine learning models were used to validate the biological significance of the key genes based on gene expression, among which five models achieved good performances [area under curve (AUC) >0.85], suggesting that our currently identified key genes are biologically significant and highly representative of genes involved in RA. Combined with other biological interpretations including Gene Ontology (GO) analysis, protein-protein interaction (PPI) network analysis, as well as inference of immune cell composition, our current study might shed a light on the in-depth study of RA diagnosis and prognosis.

Comparison of Role of Hand and Wrist Ultrasound in Diagnosis of Subclinical Synovitis in Patients with Systemic Lupus Erythematosus and Rheumatoid Arthritis: A Retrospective, Single-Center Study

Background

This retrospective study aimed to compare the roles of hand and wrist ultrasound in diagnosing subclinical synovitis in patients with systemic lupus erythematosus (SLE) and rheumatoid arthritis (RA) at a single center in Sichuan, China.

Material/Methods

Forty-one patients with SLE and 20 patients with RA were included. SLE was diagnosed using the American rheumatology Society (ACR) classification standard. Severity of SLE was evaluated using the SLE disease activity index (SLEDAI). General and clinical manifestations and laboratory indicators were measured. Spearman correlation analysis was used for analyzing correlations between musculoskeletal ultrasound results and indexes.

Results

Among 41 patients with SLE, 26 (63.4%) had joint pain, and 39 (95.1%) had at least 1 joint abnormality. Thirteen patients with SLE (31.7%) had wrist joint involvement, 7 (17.1%) had metacarpal phalangeal-1 (MCP1) involvement, 8 (19.5%) had MCP2 involvement, 17 (41.5%) had MCP3 involvement, 14 (34.1%) had MCP4 involvement, and 5 (12.2%) had MCP5 involvement. Meanwhile, 2 (4.8%) had proximal interphalangeal-1 (PIP1) involvement, 10 (24.4%) had PIP2 involvement, 17 (41.5%) had PIP3 involvement, 12 (29.3%) had PIP4 involvement, and 3 (7.3%) had PIP4 involvement. Twelve patients demonstrated knee joint involvement. MCP joints had the highest involvement frequency (P=0.003). The most frequently detected disease was synovitis, followed by tenosynovitis, joint effusion, and bone erosion. ESR (P=0.002), CRP (P=0.020), and SLEDAI (P=0.011) of patients with SLE with arthralgia were significantly higher compared to patients without arthralgia. In patients with RA, musculoskeletal ultrasound scores were correlated with erythrocyte sedimentation rate (ESR), C-reactive protein (CRP), disease activity score-28 (DAS28), and interleukin-6 (IL-6). In patients with SLE, musculoskeletal ultrasound scores were correlated with double-stranded DNA (dsDNA), ribonucleoprotein (RNP), DAS28, and IL-6.

Conclusions

Musculoskeletal ultrasound is highly sensitive in evaluating subclinical synovitis in patients with SLE, and its score is positively correlated with dsDNA, RNP IL-6, and DAS28 in patients with SLE.

Dysbiosis of oral microbiota is associated with systemic lupus erythematosus

OBJECTIVE

The important role of intestinal microbiota in systemic lupus erythematosus (SLE) has been recognized. Oral-gut microbiome axis is a crucial link in human health and disease, but few researches indicated the relationship between oral microorganisms and SLE. This study mainly explored the composition and changes of oral microorganisms in SLE patients with different stages, clinical manifestations and biomarkers.

DESIGN

Oral microbiota was detected by 16S ribosomal RNA gene sequencing from 20 SLE patients and 19 healthy controls (HCs). The evenness, diversity and composition of oral microbiota were analyzed. Moreover, receiver-operating characteristic analysis was conducted. Phylogenetic Investigation of Communities by Reconstruction of Unobserved States (PICRUSt) based on Kyoto Encyclopedia of Genes and Genomes (KEGG) database was used to investigate microbiota functions.

RESULTS

The oral microbiota of SLE patients was imbalanced and the diversity was decreased, but no difference was found between new-onset and treated SLE patients. Families Lactobacillaceae, Veillonellaceae and Moraxellaceae were enriched in SLE patients. Families like Corynebacteriaceae, Micrococcaceae, Defluviitaleaceae, Caulobacteraceae, Phyllobacteriaceae, Methylobacteriaceae, Hyphomicrobiaceae, Sphingomonadaceae, Halomonadaceae, Pseudomonadaceae, Xanthomonadaceae, etc. were decreased in SLE patients. After multiple testing adjustment, families Sphingomonadaceae, Halomonadaceae, and Xanthomonadaceae were significantly decreased in SLE patients. And area under the curve was 0.953 (95% confidence intervals 0.890-1.000) to distinguish SLE patients from HCs. There were differences in metabolic pathways between SLE and HCs (P = 0.025).

CONCLUSIONS

These findings collectively support that oral microbiota dysbiosis and aberrant metabolic pathways were observed in patients with SLE. Our findings may provide suggestive evidences for the diagnosis and treatment of SLE.

Precision health: A pragmatic approach to understanding and addressing key factors in autoimmune diseases

The past decade has witnessed a significant paradigm shift in the clinical approach to autoimmune diseases, lead primarily by initiatives in precision medicine, precision health and precision public health initiatives. An understanding and pragmatic implementation of these approaches require an understanding of the drivers, gaps and limitations of precision medicine. Gaining the trust of the public and patients is paramount but understanding that technologies such as artificial intelligences and machine learning still require context that can only be provided by human input or what is called augmented machine learning. The role of genomics, the microbiome and proteomics, such as autoantibody testing, requires continuing refinement through research and pragmatic approaches to their use in applied precision medicine.

A systematic review of the applications of artificial intelligence and machine learning in autoimmune diseases

Autoimmune diseases are chronic, multifactorial conditions. Through machine learning (ML), a branch of the wider field of artificial intelligence, it is possible to extract patterns within patient data, and exploit these patterns to predict patient outcomes for improved clinical management. Here, we surveyed the use of ML methods to address clinical problems in autoimmune disease. A systematic review was conducted using MEDLINE, embase and computers and applied sciences complete databases. Relevant papers included "machine learning" or "artificial intelligence" and the autoimmune diseases search term(s) in their title, abstract or key words. Exclusion criteria: studies not written in English, no real human patient data included, publication prior to 2001, studies that were not peer reviewed, non-autoimmune disease comorbidity research and review papers. 169 (of 702) studies met the criteria for inclusion. Support vector machines and random forests were the most popular ML methods used. ML models using data on multiple sclerosis, rheumatoid arthritis and inflammatory bowel disease were most common. A small proportion of studies (7.7% or 13/169) combined different data types in the modelling process. Cross-validation, combined with a separate testing set for more robust model evaluation occurred in 8.3% of papers (14/169). The field may benefit from adopting a best practice of validation, cross-validation and independent testing of ML models. Many models achieved good predictive results in simple scenarios (e.g. classification of cases and controls). Progression to more complex predictive models may be achievable in future through integration of multiple data types.

Applied machine learning and artificial intelligence in rheumatology

Machine learning as a field of artificial intelligence is increasingly applied in medicine to assist patients and physicians. Growing datasets provide a sound basis with which to apply machine learning methods that learn from previous experiences. This review explains the basics of machine learning and its subfields of supervised learning, unsupervised learning, reinforcement learning and deep learning. We provide an overview of current machine learning applications in rheumatology, mainly supervised learning methods for e-diagnosis, disease detection and medical image analysis. In the future, machine learning will be likely to assist rheumatologists in predicting the course of the disease and identifying important disease factors. Even more interestingly, machine learning will probably be able to make treatment propositions and estimate their expected benefit (e.g. by reinforcement learning). Thus, in future, shared decision-making will not only include the patient’s opinion and the rheumatologist’s empirical and evidence-based experience, but it will also be influenced by machine-learned evidence.

Antibodies against carbamylated vimentin exist in systemic lupus erythematosus and correlate with disease activity

OBJECTIVES

Antibodies against carbamylated protein (anti-CarP) were found to be a promising marker to evaluate joint damage and disease activity in patients with rheumatoid arthritis (RA). However, whether anti-CarP antibodies were present in systemic lupus erythematosus (SLE) remained ambiguous. We have therefore undertaken this study to assess the levels of serum anti-CarP antibodies and to evaluate their clinical value in SLE.

METHODS

Serum levels of antibodies against carbamylated-vimentin (anti-Carp) were measured by enzyme immunosorbent assay in 100 patients with SLE, 76 with RA, 17 with primary Sjögren syndrome (pSS), and 68 healthy controls. Data analyses between anti-Carp antibodies and other laboratory measures were performed using SPSS 24 software for Windows.

RESULTS

The levels of serum anti-CarP antibodies in patients with SLE were significantly higher than those in healthy controls. In addition, anti-CarP antibodies were present in SLE patients lacking the disease-specific antibodies, including anti-Smith-negative patients (24.4%, 21/86), anti-dsDNA-negative patients (29.3%, 12/41), anti-nucleosome-negative patients (21.4%, 9/42), and antiribosomal P protein antibody-negative patients (23.7%, 18/76). There were significant differences between the anti-CarP-positive and anti-CarP-negative SLE patients in clinical and laboratory features, such as age, erythrocyte sedimentation rate (ESR), C-reactive protein, rheumatoid factor, third-generation cyclic citrullinated peptide (CCP3), anticardiolipin, D-dipolymer, complement 3, immunoglobulin G (IgG), red blood cell count (RBC) and hemoglobin. After adjusting for age and disease duration, the high levels of anti-CarP antibodies were still correlated with low RBC, hemoglobin and high ESR, IgG and CCP3. Active SLE patients demonstrated higher anti-CarP IgG than inactive patients. Moreover, the levels of anti-CarP were significantly higher in SLE patients with arthralgia and/or arthritis than in those without joint involvement.

CONCLUSIONS

Anti-CarP antibodies were present in SLE patients and associated with the disease severity. These might provide a potential supplement to other specific autoantibodies for diagnosis of SLE and serve as a promising marker for measuring joint damage in the disease.

An Overview of the Intrinsic Role of Citrullination in Autoimmune Disorders

A protein undergoes many types of posttranslation modification. Citrullination is one of these modifications, where an arginine amino acid is converted to a citrulline amino acid. This process depends on catalytic enzymes such as peptidylarginine deiminase enzymes (PADs). This modification leads to a charge shift, which affects the protein structure, protein-protein interactions, and hydrogen bond formation, and it may cause protein denaturation. The irreversible citrullination reaction is not limited to a specific protein, cell, or tissue. It can target a wide range of proteins in the cell membrane, cytoplasm, nucleus, and mitochondria. Citrullination is a normal reaction during cell death. Apoptosis is normally accompanied with a clearance process via scavenger cells. A defect in the clearance system either in terms of efficiency or capacity may occur due to massive cell death, which may result in the accumulation and leakage of PAD enzymes and the citrullinated peptide from the necrotized cell which could be recognized by the immune system, where the immunological tolerance will be avoided and the autoimmune disorders will be subsequently triggered. The induction of autoimmune responses, autoantibody production, and cytokines involved in the major autoimmune diseases will be discussed.