Development of Biomarker Models to Predict Outcomes in Lupus Nephritis

Gene-Based Predictive Modelling for Enhanced Detection of Systemic Lupus Erythematosus Using CNN-Based DL Algorithm

Systemic Lupus Erythematosus (SLE) is a multifaceted autoimmune disease that presents with a diverse array of clinical signs and unpredictable disease progression. Conventional diagnostic methods frequently fall short in terms of sensitivity and specificity, which can result in delayed diagnosis and less-than-optimal management. In this study, we introduce a novel approach for improving the identification of SLE through the use of gene-based predictive modelling and Stacked deep learning classifiers. The study proposes a new method for diagnosing SLE using Stacked Deep Learning Classifiers (SDLC) trained on Gene Expression Omnibus (GEO) database data. By combining transcriptomic data from GEO with clinical features and laboratory results, the SDLC model achieves a remarkable accuracy value of 0.996, outperforming traditional methods. Individual models within the SDLC, such as SBi-LSTM and ACNN, achieved accuracies of 92% and 95%, respectively. The SDLC's ensemble learning approach allows for identifying complex patterns in multi-modal data, enhancing accuracy in diagnosing SLE. This study emphasises the potential of deep learning methods, in conjunction with open repositories like GEO, to advance the diagnosis and management of SLE. Overall, this research shows strong performance and potential for improving precision medicine in managing SLE.

Advancing Point-of-Care Diagnosis: Digitalizing Combinatorial Biomarker Signals for Lupus Nephritis

To improve the efficiency and patient coverage of the current healthcare system, user-friendly novel homecare devices are urgently needed. In this work, we developed a smartphone-based analyzing and reporting system (SBARS) for biomarker detection in lupus nephritis (LN). This system offers a cost-effective alternative to traditional, expensive large equipment in signal detection and quantification. This innovative approach involves using a portable and affordable microscopic reader to capture biomarker signals. Through smartphone-based image processing techniques, the intensity of each biomarker signal is analyzed. This system exhibited comparable performance to a commercial Genepix scanner in the detection of two potential novel biomarkers of LN, VISG4 and TNFRSF1b. Importantly, this smartphone-based analyzing and reporting system allows for discriminating LN patients with active renal disease from healthy controls with the area-under-the-curve (AUC) value = 0.9 for TNFRSF1b and 1.0 for VSIG4, respectively, indicating high predictive accuracy.

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.

Lupus Nephritis Biomarkers: A Critical Review

Lupus nephritis (LN), a major complication in individuals diagnosed with systemic lupus erythematosus, substantially increases morbidity and mortality. Despite marked improvements in the survival of patients with severe LN over the past 50 years, complete clinical remission after immunosuppressive therapy is achieved in only half of the patients. Therefore, timely detection of LN is vital for initiating prompt therapeutic interventions and improving patient outcomes. Biomarkers have emerged as valuable tools for LN detection and monitoring; however, the complex role of these biomarkers in LN pathogenesis remains unclear. Renal biopsy remains the gold standard for the identification of the histological phenotypes of LN and guides disease management. However, the molecular pathophysiology of specific renal lesions remains poorly understood. In this review, we provide a critical, up-to-date overview of the latest developments in the field of LN biomarkers.

Endothelial cell activation and glycocalyx shedding - potential as biomarkers in patients with lupus nephritis

Lupus nephritis (LN) is a common and severe manifestation of systemic lupus erythematosus and an important cause of acute and chronic kidney injury. Early diagnosis of LN and preventing relapses are key to preserving renal reserve. However, due to the complexity and heterogeneity of the disease, clinical management remains challenging. Kidney biopsy remains the gold standard for confirming the diagnosis of LN and subsequent assessment of kidney histopathology, but it is invasive and cannot be repeated frequently. Current clinical indicators of kidney function such as proteinuria and serum creatinine level are non-specific and do not accurately reflect histopathological changes, while anti-dsDNA antibody and C3 levels reflect immunological status but not kidney injury. Identification of novel and specific biomarkers for LN is prerequisite to improve management. Renal function deterioration is associated with changes in the endothelial glycocalyx, a delicate gel-like layer located at the interface between the endothelium and bloodstream. Inflammation induces endothelial cell activation and shedding of glycocalyx constituents into the circulation. This review discusses the potential role of soluble glycocalyx components as biomarkers of active LN, especially in patients in whom conventional serological and biochemical markers do not appear helpful.

Four trajectories of 24-hour urine protein levels in real-world lupus nephritis cohorts

OBJECTIVES

A 24-hour urine protein (24hUP) is a key measurement in the management of lupus nephritis (LN); however, trajectories of 24hUP in LN is poorly defined.

METHODS

Two LN cohorts that underwent renal biopsies at Renji Hospital were included. Patients received standard of care in a real-world setting and 24hUP data were collected over time. Trajectory patterns of 24hUP were determined using the latent class mixed modelling (LCMM). Baseline characters were compared among trajectories and multinomial logistic regression was used to determine independent risk factors. Optimal combinations of variables were identified for model construction and user-friendly nomograms were developed.

RESULTS

The derivation cohort composed of 194 patients with LN with 1479 study visits and a median follow-up of 17.5 (12.2-21.7) months. Four trajectories of 24hUP were identified, that is, Rapid Responders, Good Responders, Suboptimal Responders and Non-Responders, with the KDIGO renal complete remission rates (time to complete remission, months) of 84.2% (4.19), 79.6% (7.94), 40.4% (not applicable) and 9.8% (not applicable), respectively (p<0.001). The 'Rapid Responders' distinguish itself from other trajectories and a nomogram, composed of age, systemic lupus erythematosus duration, albumin and 24hUP yielded C-indices >0.85. Another nomogram to predict 'Good Responders' yielded C-indices of 0.73~0.78, which composed of gender, new-onset LN, glomerulosclerosis and partial remission within 6 months. When applied to the validation cohort with 117 patients and 500 study visits, nomograms effectively sorted out 'Rapid Responders' and 'Good Responders'.

CONCLUSION

Four trajectories of LN shed some light to guide the management of LN and further clinical trials design.

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.

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).

Artificial intelligence in glomerular diseases

In this narrative review, we focus on the application of artificial intelligence in the clinical history of patients with glomerular disease, digital pathology in kidney biopsy, renal ultrasonography imaging, and prediction of chronic kidney disease (CKD). With the development of natural language processing, the clinical history of a patient can be used to identify a computable phenotype. In kidney pathology, digital imaging has adopted innovative deep learning algorithms (DLAs) that can improve the predictive capability of the examined lesions. However, at this time, these applications can only be used in research because there is no recognized validation to replace the conventional diagnostic applications. Kidney ultrasonography, used in the clinical examination of patients, provides information about the progression of kidney damage. Machine learning algorithms (MLAs) with promising results for the early detection of CKD have been proposed, but, still, they are not solid enough to be incorporated into the clinical practice. A few tools for glomerulonephritis, based on MLAs, are available in clinical practice. They can be downloaded on computers and cellular phones but can only be applied to uniracial cohorts of patients. To improve their performance, it is necessary to organize large consortia with multiracial cohorts. Finally, in many studies MLA development has been carried out using retrospective cohorts. The performance of the models might differ in retrospective cohorts compared to real-world data. Therefore, the models should be validated in prospective external large cohorts.

Clinical predictive model to estimate probability of remission in patients with lupus nephritis

BACKGROUND

Lupus nephritis (LN) is a major organ complication and cause of morbidity and mortality in patients with systemic lupus erythematosus. This study aims to provide the clinician with a quantitative tool for the prediction of the individual remission probability of LN and obtain new insights for improved clinical management in LN treatment.

METHODS

A total of 301 patients with renal biopsy-proven LN were recruited and randomly divided into model construction and validation group. The least absolute shrinkage and selection operator regression analysis was conducted to select significant variables, and a multivariate Cox regression predictive model was established. The performance of the model was verified and tested with 1000-bootstrap validation in the validation group. Finally, the nomogram was constructed, and the performance was evaluated. The predictive accuracy and efficiency were verified through receiver operation characteristic and calibration curves.

RESULTS

A total of 210 and 91 patients who all received renal biopsy were included in the training and validation group, respectively. A final prognostic model was established, which included the course of LN, gender, 24h-proteinuria, creatinine, triglycerides, FIB, Complement C3, anti-dsDNA antibody, tubular atrophy and classification of kidney biopsy. Moreover, an easy-to-use nomogram was built based on the predictive model. The areas under the curve (AUC) of the 1, 2, 5-year prediction were 77.12, 77.98 and 87.01 in the training group, respectively. In the validation group, the AUC of the 1, 2, 5-year prediction were 81.42, 87.20 and 92.81 respectively, which indicated good performance in predicting the remission probability of LN.

CONCLUSION

This novel model was constructed to predict the remission probability of patients with LN for the first time. This model displayed good predictive performance and was easy to use for clinical practice.

Prediction models of treatment response in lupus nephritis

In order to develop prediction models of one-year treatment response in lupus nephritis, an approach using machine learning to combine traditional clinical data and novel urine biomarkers was undertaken. Contemporary lupus nephritis biomarkers were identified through an unbiased PubMed search. Thirteen novel urine proteins contributed to the top 50% of ranked biomarkers and were selected for measurement at the time of lupus nephritis flare. These novel markers along with traditional clinical data were incorporated into a variety of machine learning algorithms to develop prediction models of one-year proteinuria and estimated glomerular filtration rate (eGFR). Models were trained on 246 individuals from four different sub-cohorts and validated on an independent cohort of 30 patients with lupus nephritis. Seven models were considered for each outcome. Three-quarters of these models demonstrated good predictive value with areas under the receiver operating characteristic curve over 0.7. Overall, prediction performance was the best for models of eGFR response to treatment. Furthermore, the best performing models contained both traditional clinical data and novel urine biomarkers, including cytokines, chemokines, and markers of kidney damage. Thus, our study provides further evidence that a machine learning approach can predict lupus nephritis outcomes at one year using a set of traditional and novel biomarkers. However, further validation of the utility of machine learning as a clinical decision aid to improve outcomes will be necessary before it can be routinely used in clinical practice to guide therapy.

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.

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.

Development of a lupus nephritis suboptimal response prediction tool using renal histopathological and clinical laboratory variables at the time of diagnosis

Objective

Lupus nephritis (LN) is an immune complex-mediated glomerular and tubulointerstitial disease in patients with SLE. Prediction of outcomes at the onset of LN diagnosis can guide decisions regarding intensity of monitoring and therapy for treatment success. Currently, no machine learning model of outcomes exists. Several outcomes modelling works have used univariate or linear modelling but were limited by the disease heterogeneity. We hypothesised that a combination of renal pathology results and routine clinical laboratory data could be used to develop and to cross-validate a clinically meaningful machine learning early decision support tool that predicts LN outcomes at approximately 1 year.

Methods

To address this hypothesis, patients with LN from a prospective longitudinal registry at the Medical University of South Carolina enrolled between 2003 and 2017 were identified if they had renal biopsies with International Society of Nephrology/Renal Pathology Society pathological classification. Clinical laboratory values at the time of diagnosis and outcome variables at approximately 1 year were recorded. Machine learning models were developed and cross-validated to predict suboptimal response.

Results

Five machine learning models predicted suboptimal response status in 10 times cross-validation with receiver operating characteristics area under the curve values >0.78. The most predictive variables were interstitial inflammation, interstitial fibrosis, activity score and chronicity score from renal pathology and urine protein-to-creatinine ratio, white blood cell count and haemoglobin from the clinical laboratories. A web-based tool was created for clinicians to enter these baseline clinical laboratory and histopathology variables to produce a probability score of suboptimal response.

Conclusion

Given the heterogeneity of disease presentation in LN, it is important that risk prediction models incorporate several data elements. This report provides for the first time a clinical proof-of-concept tool that uses the five most predictive models and simplifies understanding of them through a web-based application.

Clinico-pathological associations of serum VCAM-1 and ICAM-1 levels in patients with lupus nephritis

OBJECTIVE

We investigated the clinico-pathological associations of serum VCAM-1 and ICAM-1 levels in patients with biopsy-proven Class III/IV±V lupus nephritis (LN).

METHODS

Serum VCAM-1 and ICAM-1 levels were determined by ELISAs. Sera from patients with non-renal SLE or non-lupus chronic kidney disease (CKD), and healthy subjects served as controls.

RESULTS

Seropositivity rate for VCAM-1 and ICAM-1 was 93.10% and 37.93% respectively at the time of nephritic flare, and 44.83% and 13.79% respectively at remission, with both showing higher levels during flare (P < 0.05, for both). VCAM-1 level correlated with proteinuria, serum creatinine, and anti-dsDNA antibodies, and inversely correlated with C3. VCAM-1 level also correlated with leukocyte infiltration and fibrinoid necrosis/karyorrhexis scores in active LN kidney biopsies. ICAM-1 level correlated with proteinuria, but not anti-dsDNA or C3, nor histopathological features. VCAM-1 level increased 4.5 months before renal flare, while ICAM-1 increase coincided with flare, and both decreased after treatment. ROC analysis showed that VCAM-1 distinguished active LN from healthy subjects, LN in remission, active non-renal lupus, and CKD (ROC AUC of 0.98, 0.86, 0.93 and 0.90 respectively). VCAM-1 level in combination with either proteinuria or C3 was superior in distinguishing active LN from remission compared to the measurement of individual markers. Serum ICAM-1 level distinguished active LN from healthy subjects and LN patients in remission (ROC AUC of 0.75 and 0.66 respectively), but did not distinguish between renal versus non-renal lupus. ICAM-1 level in combination with markers of endothelial cell activation (syndecan-1, hyaluronan and thrombomodulin) was superior to proteinuria, anti-dsDNA, or C3 in distinguishing active LN from quiescent disease.

CONCLUSION

Our findings suggest potential utility of serum VCAM-1 and ICAM-1 in clinical management. Monitoring VCAM-1 may facilitate early diagnosis of flare. Combining selected biomarkers may be advantageous in diagnosing active LN. VCAM-1 may have a pathogenic role in renal parenchymal inflammation in active LN.

Variable selection methods for identifying predictor interactions in data with repeatedly measured binary outcomes

Introduction:

Identifying predictors of patient outcomes evaluated over time may require modeling interactions among variables while addressing within-subject correlation. Generalized linear mixed models (GLMMs) and generalized estimating equations (GEEs) address within-subject correlation, but identifying interactions can be difficult if not hypothesized a priori. We evaluate the performance of several variable selection approaches for clustered binary outcomes to provide guidance for choosing between the methods.

Methods:

We conducted simulations comparing stepwise selection, penalized GLMM, boosted GLMM, and boosted GEE for variable selection considering main effects and two-way interactions in data with repeatedly measured binary outcomes and evaluate a two-stage approach to reduce bias and error in parameter estimates. We compared these approaches in real data applications: hypothermia during surgery and treatment response in lupus nephritis.

Results:

Penalized and boosted approaches recovered correct predictors and interactions more frequently than stepwise selection. Penalized GLMM recovered correct predictors more often than boosting, but included many spurious predictors. Boosted GLMM yielded parsimonious models and identified correct predictors well at large sample and effect sizes, but required excessive computation time. Boosted GEE was computationally efficient and selected relatively parsimonious models, offering a compromise between computation and parsimony. The two-stage approach reduced the bias and error in regression parameters in all approaches.

Conclusion:

Penalized and boosted approaches are effective for variable selection in data with clustered binary outcomes. The two-stage approach reduces bias and error and should be applied regardless of method. We provide guidance for choosing the most appropriate method in real applications.

Lupus serum induces inflammatory interaction with neutrophils in human glomerular endothelial cells

OBJECTIVES

SLE is associated with endothelial cell dysfunction (ECD). Understanding how ECD leads to neutrophil infiltration into glomeruli is essential to finding therapeutic targets for SLE. The aim of this study is to determine the effect of SLE serum from patients with active disease to induce neutrophil adhesion to and chemotaxis towards glomerular endothelial cells and factors induced by serum that associate with neutrophil chemotaxis.

METHODS

Patients with SLE had serum collected during paired longitudinal visits with lower and higher activity. 13 patients with SLE (5 SLE, 5 SLE with hypertension (HTN) and 3 SLE lupus nephritis (LN) and HTN), and 10 healthy controls (5 with and 5 without HTN) were examined. The adhesion of neutrophils to serum-treated human renal glomerular endothelial cells (HRGECs) or chemotaxis of neutrophils towards conditioned media from serum-treated HRGECs was determined, and levels of cytokines in this conditioned medium were quantified. Pathway analysis of cytokines induced by SLE and LN serum that associated with neutrophil migration was performed.

RESULTS

HRGECs treated with SLE serum induced significantly greater neutrophil chemotaxis and adhesion compared with control serum. When examining specific cohorts, SLE HTN and LN HTN promoted greater neutrophil chemotaxis than control serum, while SLE HTN and LN HTN promoted greater chemotaxis than SLE serum. Serum from active disease visits promoted neutrophil chemotaxis and adhesion over paired inactive visits. Levels of platelet-derived growth factor-BB, interleukin (IL)-15 and IL-8 secreted by SLE serum-treated HRGECs positively correlated with neutrophil chemotaxis. Pathway analysis suggested that LN serum induced pathways important in endoplasmic reticulum and oxidative stress.

CONCLUSIONS

SLE serum induces expression of mediators by HRGECs that promote neutrophil chemotaxis and adhesion, which increases during disease activity, and associates with factors common to pathways of endoplasmic reticulum and oxidative stress. These findings highlight the potential importance of serum factor-induced ECD in SLE and LN.

Disease-associated and patient-specific immune cell signatures in juvenile-onset systemic lupus erythematosus: patient stratification using a machine-learning approach

BACKGROUND

Juvenile-onset systemic lupus erythematosus (SLE) is a rare autoimmune rheumatic disease characterised by more severe disease manifestations, earlier damage accrual, and higher mortality than in adult-onset SLE. We aimed to use machine-learning approaches to characterise the immune cell profile of patients with juvenile-onset SLE and investigate links with the disease trajectory over time.

METHODS

This study included patients who attended the University College London Hospital (London, UK) adolescent rheumatology service, had juvenile-onset SLE according to the 1997 American College of Rheumatology revised classification criteria for lupus or the 2012 Systemic Lupus International Collaborating Clinics criteria, and were diagnosed before 18 years of age. Blood donated by healthy age-matched and sex-matched volunteers who were taking part in educational events in the Centre for Adolescent Rheumatology Versus Arthritis at University College London (London, UK) was used as a control. Immunophenotyping profiles (28 immune cell subsets) of peripheral blood mononuclear cells from patients with juvenile-onset SLE and healthy controls were determined by flow cytometry. We used balanced random forest (BRF) and sparse partial least squares-discriminant analysis (sPLS-DA) to assess classification and parameter selection, and validation was by ten-fold cross-validation. We used logistic regression to test the association between immune phenotypes and k-means clustering to determine patient stratification. Retrospective longitudinal clinical data, including disease activity and medication, were related to the immunological features identified.

FINDINGS

Between Sept 5, 2012, and March 7, 2018, peripheral blood was collected from 67 patients with juvenile-onset SLE and 39 healthy controls. The median age was 19 years (IQR 13-25) for patients with juvenile-onset SLE and 18 years (16-25) for healthy controls. The BRF model discriminated patients with juvenile-onset SLE from healthy controls with 90·9% prediction accuracy. The top-ranked immunological features from the BRF model were confirmed using sPLS-DA and logistic regression, and included total CD4, total CD8, CD8 effector memory, and CD8 naive T cells, Bm1, and unswitched memory B cells, total CD14 monocytes, and invariant natural killer T cells. Using these markers patients were clustered into four distinct groups. Notably, CD8 T-cell subsets were important in driving patient stratification, whereas B-cell markers were similarly expressed across the cohort of patients with juvenile-onset SLE. Patients with juvenile-onset SLE and elevated CD8 effector memory T-cell frequencies had more persistently active disease over time, as assessed by the SLE disease activity index 2000, and this was associated with increased treatment with mycophenolate mofetil and an increased prevalence of lupus nephritis. Finally, network analysis confirmed the strong association between immune phenotype and differential clinical features.

INTERPRETATION

Machine-learning models can define potential disease-associated and patient-specific immune characteristics in rare disease patient populations. Immunological association studies are warranted to develop data-driven personalised medicine approaches for treatment of patients with juvenile-onset SLE.

FUNDING

Lupus UK, The Rosetrees Trust, Versus Arthritis, and UK National Institute for Health Research University College London Hospital Biomedical Research Centre.

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.

The immune podocyte

PURPOSE OF REVIEW

Lupus nephritis (LN) is a serious manifestation of systemic lupus erythematosus and is characterized by proteinuria and renal failure. Proteinuria is a marker of poor prognosis and is attributed to podocyte loss and dysfunction. It is often debated whether these cells are innocent bystanders or active participants in the pathogenesis of glomerulonephritis.

RECENT FINDINGS

Podocytes share many elements of the innate and adaptive immune system. Specifically, they produce and express complement components and receptors which when dysregulated appear to contribute to podocyte damage and LN. In parallel, podocytes express major histocompatibility complex and co-stimulatory molecules which may be involved in local immune events. Podocyte-specific cytotoxic cells and possibly other immune cells contribute to glomerular damage. Autoantibodies present in lupus sera enter podocytes to upregulate calcium/calmodulin kinase which in turn compromises their structure and function.

SUMMARY

More recent studies point to the restoration of podocyte function using cell targeted approaches to prevent and treat LN. These strategies along with podocyte involvement in the pathogenesis of LN will be addressed in this review.

Utilization of Biomarkers in Lupus Nephritis

Lupus nephritis (LN) occurs in up to 60% of SLE patients, and is a leading cause of disability and death. Current treatment of LN consists of a combination of high dose corticosteroids that non-specifically decrease inflammation and cytotoxic medications that reduce auto-antibody production. That combination of therapy is associated with significant side effects while remission rates remain inadequate. Since the introduction of biologics into the pharmacological armamentarium, there has been hope for less toxic and more effective therapies for LN. Unfortunately, after multiple clinical trials, no biologic has improved efficacy over standard of care therapies for LN. This is likely, in part, due to disease heterogeneity. The utilization of biomarkers in LN may provide a way to stratify patients and guide therapeutic options. In this review, we summarize traditional and novel LN biomarkers and discuss how they may be used to diagnose, stratify, and guide therapy in patients with LN, bringing precision medicine to the forefront of LN therapy.

Machine learning approaches to predict lupus disease activity from gene expression data

The integration of gene expression data to predict systemic lupus erythematosus (SLE) disease activity is a significant challenge because of the high degree of heterogeneity among patients and study cohorts, especially those collected on different microarray platforms. Here we deployed machine learning approaches to integrate gene expression data from three SLE data sets and used it to classify patients as having active or inactive disease as characterized by standard clinical composite outcome measures. Both raw whole blood gene expression data and informative gene modules generated by Weighted Gene Co-expression Network Analysis from purified leukocyte populations were employed with various classification algorithms. Classifiers were evaluated by 10-fold cross-validation across three combined data sets or by training and testing in independent data sets, the latter of which amplified the effects of technical variation. A random forest classifier achieved a peak classification accuracy of 83 percent under 10-fold cross-validation, but its performance could be severely affected by technical variation among data sets. The use of gene modules rather than raw gene expression was more robust, achieving classification accuracies of approximately 70 percent regardless of how the training and testing sets were formed. Fine-tuning the algorithms and parameter sets may generate sufficient accuracy to be informative as a standalone estimate of disease activity.

Precision medicine in lupus nephritis: can biomarkers get us there?

Patients with systemic lupus erythematosus frequently develop lupus nephritis (LN), a condition that can lead to end-stage kidney disease. Multiple serum and urine biomarkers for LN have been proposed in recent years, yet none have become incorporated into clinical use. The majority of studies have been single center with significant variability in cohorts, assays, and sample storage, leading to inconclusive results. It has become clear that no single biomarker is likely to be sufficient to diagnose LN, identify flares, and define the response to therapy and prognosis. A more likely scenario is a panel of urine, serum, tissue, and genetic biomarkers. In this review, we summarize traditional and novel biomarkers and discuss how they may be utilized in order to bring precision medicine to clinical practice in LN.

Update on the epidemiology, risk factors, and disease outcomes of systemic lupus erythematosus

Obtaining an updated view of the epidemiology, risk factors, and prognosis of systemic lupus erythematosus (SLE) is pivotal to our understanding of the disease burden. Recent community-based studies with comprehensive methodology provided more accurate disease occurrence estimates and suggested that SLE may be more frequent than previously thought. Gender, race, and socioeconomic status are important disease determinants, and there is increasing appreciation of the contribution of family history and environmental exposures in SLE susceptibility. Owing to its systemic nature, assessment of disease activity is challenging, also pertaining to efforts to improve trial endpoints for better discrimination between active drug and placebo. Notably, emerging evidence supports that remission or low disease activity states and prevention of flares are realistic targets in the management of SLE associated with improved prognosis. For the future, we anticipate that high-throughput analyses in patient cohorts will enhance the identification of robust biomarkers for diagnosis, risk stratification, and personalized treatment.

Combined utilization of untimed single urine of MCP-1 and TWEAK as a potential indicator for proteinuria in lupus nephritis: A case-control study

The aim of this study was to determine whether combined utilization of untimed single urine monocyte chemoattractant protein 1 (uMCP-1) and tumor necrosis factor (TNF)-like weak inducer of apoptosis (uTWEAK) could serve as a screening test for proteinuria in patients with lupus nephritis (LN).A case-control study that contained 39 biopsy-proven LN patients, 20 non-LN systemic lupus erythematosus (SLE) patients, and 10 healthy controls (HCs) were carried out. Correlations between uMCP-1, uTWEAK, and traditional clinical markers were analyzed by Spearman correlation test. Diagnostic values of uMCP-1, uTWEAK, and urine albumin/creatinine ratio (uACR) in the assessment of proteinuria were investigated by receiver operating characteristic (ROC) curves.Biopsy-proven LN patients showed higher levels of uMCP-1 and uTWEAK than non-LN patients. uMCP-1 and uTWEAK were elevated in renal active patients (rSLEDAI ≥4). Both uMCP-1 and uTWEAK showed significant correlation with patients' rSLEDAI, 24-hour urine proteinuria (24hr UP), and anti-double-stranded DNA (anti-dsDNA) antibodies. No correlations of these 2 biomarkers between cystatin C (Cys-C), creatinine (Cr), and blood urea nitrogen (BUN) were observed. An algorithm combining the moderate sensitivity of uMCP-1 and high specificity of uTWEAK displayed great specificity and sensitivity for proteinuria screening.Both uMCP-1 and uTWEAK were positively correlated with the impairments of LN, and the combined utility of untimed single uMCP-1 and uTWEAK might be used as potential predictors for proteinuria in LN.

Involvement of TWEAK and the NF-κB signaling pathway in lupus nephritis

Previous findings have identified that tumor necrosis factor-related weak inducer of apoptosis (TWEAK) is associated with lupus nephritis (LN) activity status; however, the mechanism involved remains unclear. The present study aimed to investigate the roles of TWEAK and the nuclear factor (NF)-κB signaling pathway in LN. TWEAK levels in the blood and urine of patients with LN or non-LN systemic lupus erythematosus were measured by ELISA and compared with those in healthy controls. TWEAK expression and NF-κB transcriptional activity in the kidney were detected by western blotting, and Ki-67 and cluster of differentiation (CD) 68 expression were assessed using immunofluorescence. Additionally, human mesangial cells (HMCs) were cultured in vitro and divided into five groups: Normal control, TWEAK stimulus group, TWEAK + TWEAK blocking antibody, TWEAK + NF-κB inhibitor (BAY 11-7082) and TWEAK + combined (blocking antibody + BAY 11-7082). Cell cycle activity and Ki-67 expression in the HMCs were evaluated using flow cytometry, and cell induction of macrophage chemotaxis was determined by a Transwell assay. Levels of the inflammation-associated factors interleukin (IL)-6, monocyte chemotactic protein 1 (MCP-1), chemokine ligand 5 (CCL5), IL-8 and IL-10 were also detected by reverse transcription-quantitative polymerase chain reaction. It was observed that the urine levels of TWEAK in patients with LN were significantly elevated compared with those in the other groups (P<0.05). LN kidneys exhibited markedly increased cell proliferative ability, macrophage infiltration, TWEAK expression and NF-κB transcriptional activity compared with normal kidneys. Furthermore, the results indicated that treatment with recombinant TWEAK notably enhanced NF-κB transcriptional activity and significantly promoted cell proliferation and cell cycle activity (P<0.05), induced macrophage chemotaxis (P<0.05), significantly increased the expression of the chemotactic factors IL-6, IL-8, MCP-1 and CCL5 (P<0.05), and significantly reduced anti-inflammatory cytokine IL-10 mRNA expression in HMCs (P<0.05), relative to normal controls. Accordingly, blocking TWEAK function or inhibiting NF-κB activity reversed these effects. Collectively these data indicate that urine TWEAK may be considered as a novel biomarker of LN activity, and that blocking TWEAK function or NF-κB activity may effectively alleviate glomerular mesangial cell proliferation and macrophage chemotaxis.

Predictive biological markers of systemic lupus erythematosus flares: a systematic literature review

BACKGROUND

The aim of this study was to identify the most reliable biomarkers in the literature that could be used as flare predictors in systemic lupus erythematosus (SLE).

METHODS

A systematic review of the literature was performed using two databases (MEDLINE and EMBASE) through April 2015 and congress abstracts from the American College of Rheumatology and the European League Against Rheumatism were reviewed from 2010 to 2014. Two independent reviewers screened titles and abstracts and analysed selected papers in detail, using a specific questionnaire. Reports addressing the relationships between one or more defined biological test(s) and the occurrence of disease exacerbation were included in the systematic review.

RESULTS

From all of the databases, 4668 records were retrieved, of which 69 studies or congress abstracts were selected for the systematic review. The performance of seven types of biomarkers performed routinely in clinical practice and nine types of novel biological markers was evaluated. Despite some encouraging results for anti-double-stranded DNA antibodies, anti-C1q antibodies, B-lymphocyte stimulator and tumour necrosis factor-like weak inducer of apoptosis, none of the biomarkers stood out from the others as a potential gold standard for flare prediction. The results were heterogeneous, and a lack of standardized data prevented us from identifying a powerful biomarker.

CONCLUSIONS

No powerful conclusions could be drawn from this systematic review due to a lack of standardized data. Efforts should be undertaken to optimize future research on potential SLE biomarkers to develop validated candidates. Thus, we propose a standardized pattern for future studies.

Recent advances in the understanding of renal inflammation and fibrosis in lupus nephritis

Lupus nephritis is a potentially reversible cause of severe acute kidney injury and is an important cause of end-stage renal failure in Asians and patients of African or Hispanic descent. It is characterized by aberrant exaggerated innate and adaptive immune responses, autoantibody production and their deposition in the kidney parenchyma, triggering complement activation, activation and proliferation of resident renal cells, and expression of pro-inflammatory and chemotactic molecules leading to the influx of inflammatory cells, all of which culminate in destruction of normal nephrons and their replacement by fibrous tissue. Anti-double-stranded DNA (anti-dsDNA) antibody level correlates with disease activity in most patients. There is evidence that apart from mediating pathogenic processes through the formation of immune complexes, pathogenic anti-dsDNA antibodies can bind to resident renal cells and induce downstream pro-apoptotic, pro-inflammatory, or pro-fibrotic processes or a combination of these. Recent data also highlight the critical role of macrophages in acute and chronic kidney injury. Though clinically effective, current treatments for lupus nephritis encompass non-specific immunosuppression and the anti-inflammatory action of high-dose corticosteroids. The clinical and histological impact of novel biologics targeting pro-inflammatory molecules remains to be investigated. Insight into the underlying mechanisms that induce inflammatory and fibrotic processes in the kidney of lupus nephritis could present opportunities for more specific novel treatment options to improve clinical outcomes while minimizing off-target untoward effects. This review discusses recent advances in the understanding of pathogenic mechanisms leading to inflammation and fibrosis of the kidney in lupus nephritis in the context of established standard-of-care and emerging therapies.

Regulation of MiR-146a and TRAF6 in the Diagnose of Lupus Nephritis

BACKGROUND Lupus nephritis (LN) is a major complication of systemic lupus erythematosus (SLE). This study tested miR-146a and its target gene TRAF6 expression in LN patients and discussed their relationship with LN. MATERIAL AND METHODS One hundred twenty-eight LN patients and 30 healthy controls were enrolled in this study. MiR-146a and TRAF6 expression in peripheral blood mononuclear cells (PBMCs) were detected. Serum cytokines content was determined by ELISA. The diagnostic role of miR-146a and TRAF6 in LN activity was evaluated by ROC curve. The impact of miR-146a and TRAF6 on end-stage renal disease (ESRD) was compared by survival curve. The effect of miR-146a and TRAF6 on LN recurrence was analyzed. RESULTS Compared with healthy controls, miR-146a expression was significantly reduced and TRAF6 was upregulated in LN patients. The expression was related to LN activity. MiR-146a expression was negatively correlated, whereas TRAF6 was positively correlated with serum IL-1β, IL-6, IL-8, and TNF-α activity. The area under the ROC curve (AUC) of miR-146a and TRAF6 on the diagnosis of LN was 0.821 and 0.897, respectively. The AUC of miR-146a and TRAF6 on LN activity differentiation was 0.921 and 0.872, respectively. Downregulation of miR-146a and upregulation of TRAF6 increased the incidence of ESRD progression. Downregulation of miR-146a and upregulation of TRAF6 elevated the possibility of recurrence within one year. CONCLUSIONS MiR-146a declined, while TRAF6 increased in LN patients compared with healthy controls. Their expression can be used to effectively differentiate LN and evaluate activity. MiR-146a reduction and TRAF6 upregulation increased the possibility of ESRD progress and recurrence within one year.

Prediction of chronic damage in systemic lupus erythematosus by using machine-learning models

Objective

The increased survival in Systemic Lupus Erythematosus (SLE) patients implies the development of chronic damage, occurring in up to 50% of cases. Its prevention is a major goal in the SLE management. We aimed at predicting chronic damage in a large monocentric SLE cohort by using neural networks.

Methods

We enrolled 413 SLE patients (M/F 30/383; mean age ± SD 46.3±11.9 years; mean disease duration ± SD 174.6 ± 112.1 months). Chronic damage was assessed by the SLICC/ACR Damage Index (SDI). We applied Recurrent Neural Networks (RNNs) as a machine-learning model to predict the risk of chronic damage. The clinical data sequences registered for each patient during the follow-up were used for building and testing the RNNs.

Results

At the first visit in the Lupus Clinic, 35.8% of patients had an SDI≥1. For the RNN model, two groups of patients were analyzed: patients with SDI = 0 at the baseline, developing damage during the follow-up (N = 38), and patients without damage (SDI = 0). We created a mathematical model with an AUC value of 0.77, able to predict damage development. A threshold value of 0.35 (sensitivity 0.74, specificity 0.76) seemed able to identify patients at risk to develop damage.

Conclusion

We applied RNNs to identify a prediction model for SLE chronic damage. The use of the longitudinal data from the Sapienza Lupus Cohort, including laboratory and clinical items, resulted able to construct a mathematical model, potentially identifying patients at risk to develop damage.

Lupus nephritis biomarkers

Lupus nephritis (LN), a potentially destructive outcome of SLE, is a real challenge in the management of SLE because of the difficulty in diagnosing its subclinical onset and identifying relapses before serious complications set in. Conventional clinical parameters such as proteinuria, GFR, urine sediments, anti-dsDNA and complement levels are not sensitive or specific enough for detecting ongoing disease activity in lupus kidneys and early relapse of nephritis. There has long been a need for biomarkers of disease activity in LN. Such markers ideally should be capable of predicting early sub-clinical flares and could be used to gauge response to therapy, thus obviating the need for serial renal biopsies with their possible hazardous complications. Since urine can be readily obtained, it lends itself as an obvious biological substrate. In this review, the use of urine and serum as sources of lupus nephritis biomarkers is described, and the results of biomarker discovery studies using candidate and proteomic approaches are summarized.