Lupus or not? SLE Risk Probability Index (SLERPI): a simple, clinician-friendly machine learning-based model to assist the diagnosis of systemic lupus erythematosus

Machine learning techniques for prediction in pregnancy complicated by autoimmune rheumatic diseases: Applications and challenges

Autoimmune rheumatic diseases are chronic conditions affecting multiple systems and often occurring in young women of childbearing age. The diseases and the physiological characteristics of pregnancy significantly impact maternal-fetal health and pregnancy outcomes. Currently, the integration of big data with healthcare has led to the increasing popularity of using machine learning (ML) to mine clinical data for studying pregnancy complications. In this review, we introduce the basics of ML and the recent advances and trends of ML in different prediction applications for common pregnancy complications by autoimmune rheumatic diseases. Finally, the challenges and future for enhancing the accuracy, reliability, and clinical applicability of ML in prediction have been discussed. This review will provide insights into the utilization of ML in identifying and assisting clinical decision-making for pregnancy complications, while also establishing a foundation for exploring comprehensive management strategies for pregnancy and enhancing maternal and child health.

Early identification of macrophage activation syndrome secondary to systemic lupus erythematosus with machine learning

OBJECTIVE

The macrophage activation syndrome (MAS) secondary to systemic lupus erythematosus (SLE) is a severe and life-threatening complication. Early diagnosis of MAS is particularly challenging. In this study, machine learning models and diagnostic scoring card were developed to aid in clinical decision-making using clinical characteristics.

METHODS

We retrospectively collected clinical data from 188 patients with either SLE or the MAS secondary to SLE. 13 significant clinical predictor variables were filtered out using the Least Absolute Shrinkage and Selection Operator (LASSO). These variables were subsequently utilized as inputs in five machine learning models. The performance of the models was evaluated using the area under the receiver operating characteristic curve (ROC-AUC), F1 score, and F2 score. To enhance clinical usability, we developed a diagnostic scoring card based on logistic regression (LR) analysis and Chi-Square binning, establishing probability thresholds and stratification for the card. Additionally, this study collected data from four other domestic hospitals for external validation.

RESULTS

Among all the machine learning models, the LR model demonstrates the highest level of performance in internal validation, achieving a ROC-AUC of 0.998, an F1 score of 0.96, and an F2 score of 0.952. The score card we constructed identifies the probability threshold at a score of 49, achieving a ROC-AUC of 0.994 and an F2 score of 0.936. The score results were categorized into five groups based on diagnostic probability: extremely low (below 5%), low (5-25%), normal (25-75%), high (75-95%), and extremely high (above 95%). During external validation, the performance evaluation revealed that the Support Vector Machine (SVM) model outperformed other models with an AUC value of 0.947, and the scorecard model has an AUC of 0.915. Additionally, we have established an online assessment system for early identification of MAS secondary to SLE.

CONCLUSION

Machine learning models can significantly improve the diagnostic accuracy of MAS secondary to SLE, and the diagnostic scorecard model can facilitate personalized probabilistic predictions of disease occurrence in clinical environments.

Disentangling the riddle of systemic lupus erythematosus with antiphospholipid syndrome: blood transcriptome analysis reveals a less-pronounced IFN-signature and distinct molecular profiles in venous versus arterial events

INTRODUCTION

Systemic lupus erythematosus with antiphospholipid syndrome (SLE-APS) represents a challenging SLE endotype whose molecular basis remains unknown.

METHODS

We analysed whole-blood RNA-sequencing data from 299 patients with SLE (108 SLE-antiphospholipid antibodies (aPL)-positive, including 67 SLE-APS; 191 SLE-aPL-negative) and 72 matched healthy controls (HC). Pathway enrichment analysis, unsupervised weighted gene coexpression network analysis and machine learning were applied to distinguish disease endotypes.

RESULTS

Patients with SLE-APS demonstrated upregulated type I and II interferon (IFN) pathways compared with HC. Using a 100-gene random forests model, we achieved a cross-validated accuracy of 75.6% in distinguishing these two states. Additionally, the comparison between SLE-APS and SLE-aPL-negative revealed 227 differentially expressed genes, indicating downregulation of IFN-α and IFN-γ signatures, coupled with dysregulation of the complement cascade, B-cell activation and neutrophil degranulation. Unsupervised analysis of SLE transcriptome identified 21 gene modules, with SLE-APS strongly linked to upregulation of the 'neutrophilic/myeloid' module. Within SLE-APS, venous thromboses positively correlated with 'neutrophilic/myeloid' and 'B cell' modules, while arterial thromboses were associated with dysregulation of 'DNA damage response (DDR)' and 'metabolism' modules. Anticardiolipin and anti-β2GPI positivity-irrespective of APS status-were associated with the 'neutrophilic/myeloid' and 'protein-binding' module, respectively.

CONCLUSIONS

There is a hierarchical upregulation and-likely-dependence on IFN in SLE with the highest IFN signature observed in SLE-aPL-negative patients. Venous thrombotic events are associated with neutrophils and B cells while arterial events with DDR and impaired metabolism. This may account for their differential requirements for anticoagulation and provide rationale for the potential use of mTOR inhibitors such as sirolimus and the direct fIIa inhibitor dabigatran in SLE-APS.

Comparison of the SLE Risk Probability Index (SLERPI) scale against the European League Against Rheumatism/American College of Rheumatology (ACR/EULAR) and Systemic Lupus International Collaborating Clinics (SLICC) criteria

INTRODUCTION

Timely diagnosis and proper recognition of Systemic Lupus Erythematosus (SLE) is essential to establish early management in inpatients and outpatients. There are different classification scales to identify SLE, which include various clinical and serological aspects. In 2021, the SLE Risk Probability Index (SLERPI) was published, which focuses predominantly on the clinical characteristics of patients with suspected SLE and uses a simple algorithm for early recognition of the disease. The aim of this study is to compare the European League Against Rheumatism/American College of Rheumatology (ACR/EULAR) classification criteria, the Systemic Lupus International Collaborating Clinics (SLICC) criteria, and the SLERPI criteria in a cohort of Colombian patients with SLE and to analyze the correlations observed between their absolute scores.

METHODS

A registry of SLE patients from two referral hospitals in Bogotá, Colombia, was used. 2021 SLERPI, 2019 ACR/EULAR, and 2012 SLICC scores were calculated for each patient and the correlations found between the scales were analyzed. The sensitivities of each were compared, and frequency analyses were conducted among different clinical and laboratory variables.

RESULTS

Between 2016 and 2019, 146 patients diagnosed with SLE were registered, including inpatients and outpatients. The median age was 36 years (interquartile range 26-51), and 82.2% were women. According to the SLERPI criteria, a high prevalence of antinuclear antibodies (92%), immunological disorders (71%), and arthritis (64%) were observed. The most used treatments were corticosteroids (87.6%) and chloroquine (67.8%). A Spearman evaluation analysis was performed, with a moderately strong correlation of 0.76 (p = .000) between the SLERPI and ACR/EULAR scales and very strong correlation of 0.80 (p = .000) between the SLERPI and SLICC. Patients classified with SLE according to the SLERPI scale exhibited a higher incidence of hematological compromise, along with elevated levels of serological markers such as anti-DNA antibodies. Additionally, this group more commonly received treatments involving corticosteroids and azathioprine, and displayed a higher prevalence of hypertension.

CONCLUSION

The SLERPI scale could be useful in the diagnosis of SLE, especially in early stages, given its good correlation with other classification scales and its good sensitivity.

A scoping review of triage approaches for the referral of patients with suspected inflammatory arthritis, from primary to rheumatology care

We aimed to (1) identify existing triage approaches for referral of patients with suspected inflammatory arthritis (IA) from primary care physicians (PCP) to rheumatologists, (2) describe their characteristics and methodologies for clinical use, and (3) report their level of validation for use in a publicly funded healthcare system. The comprehensive search strategy of multiple databases up to October 2023 identified relevant literature and focussed on approaches applied at the PCP-Rheumatologist referral stage. Primary, quantitative studies, reported in English were included. Triage approaches were grouped into patient conditions as defined by the authors of the reports, including IA, its subtypes and combinations. 13952 records were identified, 425 full text reviewed and 55 reports of 53 unique studies were included. Heterogeneity in disease nomenclature and study sample pretest probability was found. The number of published studies rapidly increased after 2012. Studies were mostly from Europe and North America, in IA and Axial Spondyloarthritis (AxSpa). We found tools ranging the continuum of development with those best performing, indicated by the area under the receiver operating curve (AUC) >0.8), requiring only patient-reported questions. There were AUCs for some tools reported from multiple studies, these were in the outstanding to excellent range for the Early IA Questionnaire (EIAQ) (0.88 to 0.92), acceptable for the Case Finding AxSpa (CaFaSpa) (0.70 to 0.75), and poor to outstanding for the Psoriasis Epidemiology Screening Tool (PEST) (0.61 to 0.91). Given the clinical urgency to improve rheumatology referrals and considering the good.

Identifying antinuclear antibody positive individuals at risk for developing systemic autoimmune disease: development and validation of a real-time risk model

Objective

Positive antinuclear antibodies (ANAs) cause diagnostic dilemmas for clinicians. Currently, no tools exist to help clinicians interpret the significance of a positive ANA in individuals without diagnosed autoimmune diseases. We developed and validated a risk model to predict risk of developing autoimmune disease in positive ANA individuals.

Methods

Using a de-identified electronic health record (EHR), we randomly chart reviewed 2,000 positive ANA individuals to determine if a systemic autoimmune disease was diagnosed by a rheumatologist. A priori, we considered demographics, billing codes for autoimmune disease-related symptoms, and laboratory values as variables for the risk model. We performed logistic regression and machine learning models using training and validation samples.

Results

We assembled training (n = 1030) and validation (n = 449) sets. Positive ANA individuals who were younger, female, had a higher titer ANA, higher platelet count, disease-specific autoantibodies, and more billing codes related to symptoms of autoimmune diseases were all more likely to develop autoimmune diseases. The most important variables included having a disease-specific autoantibody, number of billing codes for autoimmune disease-related symptoms, and platelet count. In the logistic regression model, AUC was 0.83 (95% CI 0.79-0.86) in the training set and 0.75 (95% CI 0.68-0.81) in the validation set.

Conclusion

We developed and validated a risk model that predicts risk for developing systemic autoimmune diseases and can be deployed easily within the EHR. The model can risk stratify positive ANA individuals to ensure high-risk individuals receive urgent rheumatology referrals while reassuring low-risk individuals and reducing unnecessary referrals.

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.

SLE criteria are by necessity still based on clinical (and immunological) criteria items

INTRODUCTION

The 2019 European League Against Rheumatism/American College of Rheumatology (EULAR/ACR) classification criteria for systemic lupus erythematosus (SLE) rely on clinical and routine immunological items. The criteria have anti-nuclear antibodies (ANA) as an obligatory entry criterion; items are weighted and ordered in domains. While demonstrating good sensitivity and specificity, the lack of a more molecular approach to some came as a disappointment.

AREAS COVERED

Based on a non-systematic literature search, this review covers items investigated in the EULAR/ACR classification criteria project, but not included in the set of criteria. It demonstrates data on the importance of the criteria and analyses implications of multiomics studies started around the same time as the criteria project. We also discuss data on the type-I interferon signature and on other cytokines, as well as on complement proteins and their split products. The final part deals with the variability in disease and the apparently random pattern of autoantibodies and organ manifestations in individual patients.

EXPERT OPINION

We believe that the EULAR/ACR criteria are a relevant step toward the right direction. A more uniform molecular approach will not be feasible as long as the molecular mechanisms underlying the tendency toward producing multiple autoantibodies are not better understood.

Classifying systemic lupus erythematosus using laboratory items alone: a preliminary study

OBJECTIVES

To explore the performance of laboratory items alone in systemic lupus erythematosus (SLE) classification.

METHODS

Our cohort consisted of 352 and 385 (control) patients with and without SLE. This study evaluated the performance of the American College of Rheumatology (ACR)-1997, Systemic Lupus International Collaborating Clinics (SLICC)-2012, European League Against Rheumatism (EULAR)/ACR-2019, and Systemic Lupus Erythematosus Risk Probability Index (SLERPI) using laboratory items alone, including blood and urine test results.

RESULTS

The median ratio of laboratory items/total items was 66.7%, 75.0%, 60.4%, and 77.4% in ACR-1997, SLICC-2012, EULAR/ACR-2019, and SLERPI, respectively. After including laboratory items alone, the sensitivity of ACR-1997, SLICC-2012, EULAR/ACR-2019, and SLERPI was 31.3% (95% confidence interval [CI]: 26.4%-36.4%), 79.8% (95% CI: 75.3%-83.9%), 75.9% (95% CI: 71.0%-80.2%), and 85.2% (95% CI: 81.1%-88.8%), respectively. We referenced the SLERPI and removed the additional restrictions, i.e., SLICC-2012 criteria only needs to fulfill at least four items (mSLICC-2012) and EULAR/ACR-2019 criteria needs to have ≥ 10 points (mEULAR/ACR-2019) to qualify for SLE classification. The mSLICC-2012 and mEULAR/ACR-2019 criteria, including laboratory items alone, newly identified 13 and 25 patients, respectively. Based on laboratory items alone, the combination of mSLICC-2012, mEULAR/ACR-2019, and SLERPI identified 348 patients with an improved sensitivity of 90.6% (95% CI: 87.1%-93.5%). Patients, who were classified according to the mEULAR/ACR-2019 criteria, all met the other criteria.

CONCLUSION

Incorporating laboratory items alone was clinically feasible to help identify SLE. SLERPI and SLICC-2012, using laboratory items alone, were more worthwhile to promote in the clinic compared with EULAR/ACR-2019. Key Points • Laboratory items play a crucial role in the SLE classification criteria, and incorporating laboratory items alone was clinically feasible to help in the identification of SLE. • The SLERPI and SLICC-2012, using laboratory items alone, were more worthwhile to promote in the clinic compared with EULAR/ACR-2019, and the combination of the two could further improve the sensitivity. • The relative simplicity of evaluating laboratory indices may help nonrheumatologists and inexperienced rheumatologists to identify SLE more quickly, thereby reducing the risk of delayed diagnosis in patients.

Clinical patterns of disease: From early systemic lupus erythematosus to late-onset disease

Systemic lupus erythematosus (SLE) is a complex disease with an insidious clinical presentation. In up to half of the cases, SLE onset is characterized by clinical and serological manifestations that, although specific, are insufficient to fulfill the classification criteria. This condition, called incomplete SLE, could be as challenging as the definite and classifiable SLE and requires to be treated according to the severity of clinical manifestations. In addition, an early SLE diagnosis and therapeutic intervention can positively influence the disease outcome, including remission rate and damage accrual. After diagnosis, the disease course is relapsing-remitting for most patients. Time in remission and cumulative glucocorticoid exposure are the most important factors for prognosis. Therefore, timely identification of SLE clinical patterns may help tailor the therapeutic intervention to the disease course. Late-onset SLE is rare but more often associated with delayed diagnosis and a higher incidence of comorbidities, including Sjogren's syndrome. This review focuses on the SLE disease course, providing actionable strategies for early diagnosis, an overview of the possible clinical patterns of SLE, and the clinical variation associated with the different age-at-onset SLE groups.

Machine learning application in autoimmune diseases: State of art and future prospectives

Autoimmune diseases are a group of disorders resulting from an alteration of immune tolerance, characterized by the formation of autoantibodies and the consequent development of heterogeneous clinical manifestations. Diagnosing autoimmune diseases is often complicated, and the available prognostic tools are limited. Machine learning allows us to analyze large amounts of data and carry out complex calculations quickly and with minimal effort. In this work, we examine the literature focusing on the use of machine learning in the field of the main systemic (systemic lupus erythematosus and rheumatoid arthritis) and organ-specific autoimmune diseases (type 1 diabetes mellitus, autoimmune thyroid, gastrointestinal, and skin diseases). From our analysis, interesting applications of machine learning emerged for developing algorithms useful in the early diagnosis of disease or prognostic models (risk of complications, therapeutic response). Subsequent studies and the creation of increasingly rich databases to be supplied to the algorithms will eventually guide the clinician in the diagnosis, allowing intervention when the pathology is still in an early stage and immediately directing towards a correct therapeutic approach.

Novel multiclass classification machine learning approach for the early-stage classification of systemic autoimmune rheumatic diseases

OBJECTIVE

Systemic autoimmune rheumatic diseases (SARDs) encompass a diverse group of complex conditions with overlapping clinical features, making accurate diagnosis challenging. This study aims to develop a multiclass machine learning (ML) model for early-stage SARDs classification using accessible laboratory indicators.

METHODS

A total of 925 SARDs patients were included, categorised into SLE, Sjögren's syndrome (SS) and inflammatory myositis (IM). Clinical characteristics and laboratory markers were collected and nine key indicators, including anti-dsDNA, anti-SS-A60, anti-Sm/nRNP, antichromatin, anti-dsDNA (indirect immunofluorescence assay), haemoglobin (Hb), platelet, neutrophil percentage and cytoplasmic patterns (AC-19, AC-20), were selected for model building. Various ML algorithms were used to construct a tripartite classification ML model.

RESULTS

Patients were divided into two cohorts, cohort 1 was used to construct a tripartite classification model. Among models assessed, the random forest (RF) model demonstrated superior performance in distinguishing SLE, IM and SS (with area under curve=0.953, 0.903 and 0.836; accuracy= 0.892, 0.869 and 0.857; sensitivity= 0.890, 0.868 and 0.795; specificity= 0.910, 0.836 and 0.748; positive predictive value=0.922, 0.727 and 0.663; and negative predictive value= 0.854, 0.915 and 0.879). The RF model excelled in classifying SLE (precision=0.930, recall=0.985, F1 score=0.957). For IM and SS, RF model outcomes were (precision=0.793, 0.950; recall=0.920, 0.679; F1 score=0.852, 0.792). Cohort 2 served as an external validation set, achieving an overall accuracy of 87.3%. Individual classification performances for SLE, SS and IM were excellent, with precision, recall and F1 scores specified. SHAP analysis highlighted significant contributions from antibody profiles.

CONCLUSION

This pioneering multiclass ML model, using basic laboratory indicators, enhances clinical feasibility and demonstrates promising potential for SARDs classification. The collaboration of clinical expertise and ML offers a nuanced approach to SARDs classification, with potential for enhanced patient care.

Systemic Lupus Erythematosus: How Machine Learning Can Help Distinguish between Infections and Flares

Systemic Lupus Erythematosus (SLE) is a multifaceted autoimmune ailment that impacts multiple bodily systems and manifests with varied clinical manifestations. Early detection is considered the most effective way to save patients' lives, but detecting severe SLE activity in its early stages is proving to be a formidable challenge. Consequently, this work advocates the use of Machine Learning (ML) algorithms for the diagnosis of SLE flares in the context of infections. In the pursuit of this research, the Random Forest (RF) method has been employed due to its performance attributes. With RF, our objective is to uncover patterns within the patient data. Multiple ML techniques have been scrutinized within this investigation. The proposed system exhibited around a 7.49% enhancement in accuracy when compared to k-Nearest Neighbors (KNN) algorithm. In contrast, the Support Vector Machine (SVM), Binary Linear Discriminant Analysis (BLDA), Decision Trees (DT) and Linear Regression (LR) methods demonstrated inferior performance, with respective values around 81%, 78%, 84% and 69%. It is noteworthy that the proposed method displayed a superior area under the curve (AUC) and balanced accuracy (both around 94%) in comparison to other ML approaches. These outcomes underscore the feasibility of crafting an automated diagnostic support method for SLE patients grounded in ML systems.

Machine learning approaches to identify systemic lupus erythematosus in anti-nuclear antibody-positive patients using genomic data and electronic health records

BACKGROUND

Although the 2019 EULAR/ACR classification criteria for systemic lupus erythematosus (SLE) has required at least a positive anti-nuclear antibody (ANA) titer (≥ 1:80), it remains challenging for clinicians to identify patients with SLE. This study aimed to develop a machine learning (ML) approach to assist in the detection of SLE patients using genomic data and electronic health records.

METHODS

Participants with a positive ANA (≥ 1:80) were enrolled from the Taiwan Precision Medicine Initiative cohort. The Taiwan Biobank version 2 array was used to detect single nucleotide polymorphism (SNP) data. Six ML models, Logistic Regression, Random Forest (RF), Support Vector Machine, Light Gradient Boosting Machine, Gradient Tree Boosting, and Extreme Gradient Boosting (XGB), were used to identify SLE patients. The importance of the clinical and genetic features was determined by Shapley Additive Explanation (SHAP) values. A logistic regression model was applied to identify genetic variations associated with SLE in the subset of patients with an ANA equal to or exceeding 1:640.

RESULTS

A total of 946 SLE and 1,892 non-SLE controls were included in this analysis. Among the six ML models, RF and XGB demonstrated superior performance in the differentiation of SLE from non-SLE. The leading features in the SHAP diagram were anti-double strand DNA antibodies, ANA titers, AC4 ANA pattern, polygenic risk scores, complement levels, and SNPs. Additionally, in the subgroup with a high ANA titer (≥ 1:640), six SNPs positively associated with SLE and five SNPs negatively correlated with SLE were discovered.

CONCLUSIONS

ML approaches offer the potential to assist in diagnosing SLE and uncovering novel SNPs in a group of patients with autoimmunity.

Leveraging machine learning to distinguish between bacterial and viral induced pharyngitis using hematological markers: a retrospective cohort study

Accurate differentiation between bacterial and viral-induced pharyngitis is recognized as essential for personalized treatment and judicious antibiotic use. From a cohort of 693 patients with pharyngitis, data from 197 individuals clearly diagnosed with bacterial or viral infections were meticulously analyzed in this study. By integrating detailed hematological insights with several machine learning algorithms, including Random Forest, Neural Networks, Decision Trees, Support Vector Machine, Naive Bayes, and Lasso Regression, for potential biomarkers were identified, with an emphasis being placed on the diagnostic significance of the Monocyte-to-Lymphocyte Ratio. Distinct inflammatory signatures associated with bacterial infections were spotlighted in this study. An innovation introduced in this research was the adaptation of the high-accuracy Lasso Regression model for the TI-84 calculator, with an AUC (95% CI) of 0.94 (0.925-0.955) being achieved. Using this adaptation, pivotal laboratory parameters can be input on-the-spot and infection probabilities can be computed subsequently. This methodology embodies an improvement in diagnostics, facilitating more effective distinction between bacterial and viral infections while fostering judicious antibiotic use.

Management of systemic lupus erythematosus: A new scenario

The introduction of targeted biological agents in systemic lupus erythematosus (SLE) has created a momentum for improving overall disease management and patients' prognosis. To achieve this, a comprehensive strategy is required spanning the entire patient journey from diagnosis to prevention and management of late complications and comorbidities. In this review, we focus on four aspects that are closely linked to SLE prognosis, namely early disease recognition and treatment initiation, reduction of the cumulative glucocorticoid exposure, attainment of well-defined targets of remission and low disease activity, prevention of flares and, kidney-protective strategies with non-immune-directed agents. We review the recent literature related to these topics in conjunction with the existing treatment recommendations, highlighting areas of uncertainty and providing guidance towards facilitating the care of SLE patients.

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.

Machine learning, a new tool for the detection of immunodeficiency patterns in systemic lupus erythematosus

Systemic lupus erythematosus (SLE) is a complex autoimmune disease that affects several organs and causes variable clinical symptoms. Early diagnosis is currently the most effective way to save the lives of patients with SLE. But it is very difficult to detect in the early stages of the disease. Because of this, this study proposes a machine learning system to help diagnose patients with SLE. To carry out the research, the extreme gradient boosting method has been implemented due to its performance characteristics, as it allows high performance, scalability, accuracy, and low computational load. From this method we try to recognize patterns in the data obtained from patients, which allow the classification of SLE patients with high accuracy and differentiate these patients from controls. Several machine learning methods have been analyzed in this study. The proposed method achieves a higher prediction value of patients who may suffer from SLE than the rest of the compared systems. The proposed algorithm achieved an improvement in accuracy of 4.49% over k-Nearest Neighbors. As for the Support Vector Machine and Gaussian Naive Bayes (GNB) methods, they achieved a lower performance than the proposed one, reaching values of 83% and 81%, respectively. It should be noted that the proposed system showed a higher area under the curve (90%) and a balanced accuracy (90%) than the other machine learning methods. This study shows the usefulness of ML techniques for identifying and predicting SLE patients. These results demonstrate the possibility of developing automatic diagnostic support systems for SLE patients based on machine learning techniques.

Systemic lupus erythematosus with high disease activity identification based on machine learning

OBJECTIVE

Clinical evaluation of systemic lupus erythematosus (SLE) disease activity is limited and inconsistent, and high disease activity significantly, seriously impacts on SLE patients. This study aims to generate a machine learning model to identify SLE patients with high disease activity.

METHOD

A total of 1014 SLE patients with low disease activity and 453 SLE patients with high disease activity were included. A total of 94 clinical, laboratory data and 17 meteorological indicators were collected. After data preprocessing, we use mutual information and multisurf to evaluate and select the importance of features. The selected features are used for machine learning modeling. Performance of the model is evaluated and verified by a series of binary classification indicators.

RESULTS

We screened out hematuria, proteinuria, pyuria, low complement, precipitation, sunlight and other features for model construction by integrated feature selection. After hyperparameter optimization, the LGB has the best performance (ROC: AUC = 0.930; PRC: AUC = 0.911, APS = 0.913; balance accuracy: 0.856), and the worst is the naive bayes (ROC: AUC = 0.849; PRC: AUC = 0.719, APS = 0.714; balance accuracy: 0.705). Finally, the selection of features has good consistency in the composite feature importance bar plot.

CONCLUSION

We identify SLE patients with high disease activity by a simple machine learning pipeline, especially the LGB model based on the characteristics of proteinuria, hematuria, pyuria and other feathers screened out by collective feature selection.

Phenotype Risk Score but Not Genetic Risk Score Aids in Identifying Individuals With Systemic Lupus Erythematosus in the Electronic Health Record

OBJECTIVE

Systemic lupus erythematosus (SLE) poses diagnostic challenges. We undertook this study to evaluate the utility of a phenotype risk score (PheRS) and a genetic risk score (GRS) to identify SLE individuals in a real-world setting.

METHODS

Using a de-identified electronic health record (EHR) database with an associated DNA biobank, we identified 789 SLE cases and 2,261 controls with available MEGAEX genotyping. A PheRS for SLE was developed using billing codes that captured American College of Rheumatology SLE criteria. We developed a GRS with 58 SLE risk single-nucleotide polymorphisms (SNPs).

RESULTS

SLE cases had a significantly higher PheRS (mean ± SD 7.7 ± 8.0 versus 0.8 ± 2.0 in controls; P < 0.001) and GRS (mean ± SD 12.2 ± 2.3 versus 11.0 ± 2.0 in controls; P < 0.001). Black individuals with SLE had a higher PheRS compared to White individuals (mean ± SD 10.0 ± 10.1 versus 7.1 ± 7.2, respectively; P = 0.002) but a lower GRS (mean ± SD 9.0 ± 1.4 versus 12.3 ± 1.7, respectively; P < 0.001). Models predicting SLE that used only the PheRS had an area under the curve (AUC) of 0.87. Adding the GRS to the PheRS resulted in a minimal difference with an AUC of 0.89. On chart review, controls with the highest PheRS and GRS had undiagnosed SLE.

CONCLUSION

We developed a SLE PheRS to identify established and undiagnosed SLE individuals. A SLE GRS using known risk SNPs did not add value beyond the PheRS and was of limited utility in Black individuals with SLE. More work is needed to understand the genetic risks of SLE in diverse populations.

Machine Learning Approach for Predicting Systemic Lupus Erythematosus in an Oman-Based Cohort

Objectives

This study aimed to design a machine learning-based prediction framework to predict the presence or absence of systemic lupus erythematosus (SLE) in a cohort of Omani patients.

Methods

Data of 219 patients from 2006 to 2019 were extracted from Sultan Qaboos University Hospital's electronic records. Among these, 138 patients had SLE, while the remaining 81 had other rheumatologic diseases. Clinical and demographic features were analysed to focus on the early stages of the disease. Recursive feature selection was implemented to choose the most informative features. The CatBoost classification algorithm was utilised to predict SLE, and the SHAP explainer algorithm was applied on top of the CatBoost model to provide individual prediction reasoning, which was then validated by rheumatologists.

Results

CatBoost achieved an area under the receiver operating characteristic curve score of 0.95 and a sensitivity of 92%. The SHAP algorithm identified four clinical features (alopecia, renal disorders, acute cutaneous lupus and haemolytic anaemia) and the patient's age as having the greatest contribution to the prediction.

Conclusion

An explainable framework to predict SLE in patients and provide reasoning for its prediction was designed and validated. This framework enables clinicians to implement early interventions that will lead to positive healthcare outcomes.

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.

Machine learning algorithm improves the detection of NASH (NAS-based) and at-risk NASH: A development and validation study

BACKGROUND AND AIMS

Detecting NASH remains challenging, while at-risk NASH (steatohepatitis and F≥ 2) tends to progress and is of interest for drug development and clinical application. We developed prediction models by supervised machine learning techniques, with clinical data and biomarkers to stage and grade patients with NAFLD.

APPROACH AND RESULTS

Learning data were collected in the Liver Investigation: Testing Marker Utility in Steatohepatitis metacohort (966 biopsy-proven NAFLD adults), staged and graded according to NASH CRN. Conditions of interest were the clinical trial definition of NASH (NAS ≥ 4;53%), at-risk NASH (NASH with F ≥ 2;35%), significant (F ≥ 2;47%), and advanced fibrosis (F ≥ 3;28%). Thirty-five predictors were included. Missing data were handled by multiple imputations. Data were randomly split into training/validation (75/25) sets. A gradient boosting machine was applied to develop 2 models for each condition: clinical versus extended (clinical and biomarkers). Two variants of the NASH and at-risk NASH models were constructed: direct and composite models.Clinical gradient boosting machine models for steatosis/inflammation/ballooning had AUCs of 0.94/0.79/0.72. There were no improvements when biomarkers were included. The direct NASH model produced AUCs (clinical/extended) of 0.61/0.65. The composite NASH model performed significantly better (0.71) for both variants. The composite at-risk NASH model had an AUC of 0.83 (clinical and extended), an improvement over the direct model. Significant fibrosis models had AUCs (clinical/extended) of 0.76/0.78. The extended advanced fibrosis model (0.86) performed significantly better than the clinical version (0.82).

CONCLUSIONS

Detection of NASH and at-risk NASH can be improved by constructing independent machine learning models for each component, using only clinical predictors. Adding biomarkers only improved the accuracy of fibrosis.

Risk and Factors associated with disease manifestations in systemic lupus erythematosus - lupus nephritis (RIFLE-LN): a ten-year risk prediction strategy derived from a cohort of 1652 patients

Objectives

Lupus nephritis (LN) remains one of the most severe manifestations in patients with systemic lupus erythematosus (SLE). Onset and overall LN risk among SLE patients remains considerably difficult to predict. Utilizing a territory-wide longitudinal cohort of over 10 years serial follow-up data, we developed and validated a risk stratification strategy to predict LN risk among Chinese SLE patients - Risk and Factors associated with disease manifestations in systemic Lupus Erythematosus - Lupus Nephritis (RIFLE-LN).

Methods

Demographic and longitudinal data including autoantibody profiles, clinical manifestations, major organ involvement, LN biopsy results and outcomes were documented. Association analysis was performed to identify factors associated with LN. Regression modelling was used to develop a prediction model for 10-year risk of LN and thereafter validated.

Results

A total of 1652 patients were recruited: 1382 patients were assigned for training and validation of the RIFLE-LN model; while 270 were assigned for testing. The median follow-up duration was 21 years. In the training and validation cohort, 845 (61%) of SLE patients developed LN. Cox regression and log rank test showed significant positive association between male sex, age of SLE onset and anti-dsDNA positivity. These factors were thereafter used to develop RIFLE-LN. The algorithm was tested in 270 independent patients and showed good performance (AUC = 0·70).

Conclusion

By using male sex, anti-dsDNA positivity, age of SLE onset and SLE duration; RIFLE-LN can predict LN among Chinese SLE patients with good performance. We advocate its potential utility in guiding clinical management and disease monitoring. Further validation studies in independent cohorts are required.

Lupus nephritis or not? A simple and clinically friendly machine learning pipeline to help diagnosis of lupus nephritis

OBJECTIVE

Diagnosis of lupus nephritis (LN) is a complex process, which usually requires renal biopsy. We aim to establish a machine learning pipeline to help diagnosis of LN.

METHODS

A cohort of 681 systemic lupus erythematosus (SLE) patients without LN and 786 SLE patients with LN was established, and a total of 95 clinical, laboratory data and 17 meteorological indicators were collected. After tenfold cross-validation, the patients were divided into training set and test set. The features selected by collective feature selection method of mutual information (MI) and multisurf were used to construct the models of logistic regression, decision tree, random forest, naive Bayes, support vector machine (SVM), light gradient boosting (LGB), extreme gradient boosting (XGB), and artificial neural network (ANN), the models were compared and verified in post-analysis.

RESULTS

Collective feature selection method screens out antistreptolysin (ASO), retinol binding protein (RBP), lupus anticoagulant 1 (LA1), LA2, proteinuria and other features, and the hyperparameter optimized XGB (ROC: AUC = 0.995; PRC: AUC = 1.000, APS = 1.000; balance accuracy: 0.990) has the best performance, followed by LGB (ROC: AUC = 0.992; PRC: AUC = 0.997, APS = 0.977; balance accuracy: 0.957). The worst performance is naive Bayes model (ROC: AUC = 0.799; PRC: AUC = 0.822, APS = 0.823; balance accuracy: 0.693). In the composite feature importance bar plots, ASO, RF, Up/Ucr, and other features play important roles in LN.

CONCLUSION

We developed and validated a new and simple machine learning pathway for diagnosis of LN, especially the XGB model based on ASO, LA1, LA2, proteinuria, and other features screened out by collective feature selection.

Annals of the Rheumatic Diseases collection on lupus nephritis (2019-2022): novel insights and advances in therapy

No single organ has received as much attention in systemic lupus erythematosus (SLE) as the kidneys. During the period 2019-2022, the Annals of the Rheumatic Diseases published several original papers, brief reports and letters that further elucidate the pathogenesis and advance the management of LN. A selection of representative original papers is highlighted in this review.

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).

Clinical response trajectories and drug persistence in systemic lupus erythematosus patients on belimumab treatment: A real-life, multicentre observational study

Objective

To obtain real-world data on outcomes of belimumab treatment and respective prognostic factors in patients with systemic lupus erythematosus (SLE).

Methods

Observational study of 188 active SLE patients (median disease duration 6.2 years, two previous immunosuppressive/biological agents) treated with belimumab, who were monitored for SLEDAI-2K, Physician Global Assessment (PGA), LLDAS (lupus low disease activity state), remission (DORIS/Padua definitions), SELENA-SLEDAI Flare Index, SLICC/ACR damage index and treatment discontinuations. Group-based disease activity trajectories were modelled followed by multinomial regression for predictive variables. Drug survival was analysed by Cox-regression.

Results

At 6, 12 and 24 months, LLDAS was attained by 36.2%, 36.7% and 33.5%, DORIS-remission by 12.3%, 11.6% and 17.8%, and Padua-remission by 21.3%, 17.9% and 29.0%, respectively (attrition-corrected). Trajectory analysis of activity indices classified patients into complete (25.5%), partial (42.0%) and non-responder (32.4%) groups, which were predicted by baseline PGA, inflammatory rash, leukopenia and prior use of mycophenolate. During median follow-up of 15 months, efficacy-related discontinuations occurred in 31.4% of the cohort, especially in patients with higher baseline PGA (hazard ratio [HR] 2.78 per 1-unit; 95% CI 1.32-5.85). Conversely, PGA improvement at 3 months predicted longer drug retention (HR 0.57; 95% CI 0.33-0.97). Use of hydroxychloroquine was associated with lower risk for safety-related drug discontinuation (HR 0.33; 95% CI 0.13-0.85). Although severe flares were reduced, flares were not uncommon (58.0%) and contributed to treatment stops (odds ratio [OR] 1.73 per major flare; 95% CI 1.09-2.75) and damage accrual (OR 1.83 per mild/moderate flare; 95% CI 1.15-2.93).

Conclusions

In a real-life setting with predominant long-standing SLE, belimumab was effective in the majority of patients, facilitating the achievement of therapeutic targets. Monitoring PGA helps to identify patients who will likely benefit and stay on the treatment. Vigilance is required for the prevention and management of flares while on belimumab.

Artificial neural network - an effective tool for predicting the lupus nephritis outcome

Background

Lupus nephropathy (LN) occurs in approximately 50% of patients with systemic lupus erythematosus (SLE), and 20% of them will eventually progress into end-stage renal disease (ESRD). A clinical tool predicting remission of proteinuria might be of utmost importance. In our work, we focused on predicting the chance of complete remission achievement in LN patients, using artificial intelligence models, especially an artificial neural network, called the multi-layer perceptron.

Methods

It was a single centre retrospective study, including 58 individuals, with diagnosed systemic lupus erythematous and biopsy proven lupus nephritis. Patients were assigned into the study cohort, between 1st January 2010 and 31st December 2020, and eventually randomly allocated either to the training set (N = 46) or testing set (N = 12). The end point was remission achievement. We have selected an array of variables, subsequently reduced to the optimal minimum set, providing the best performance.

Results

We have obtained satisfactory results creating predictive models allowing to assess, with accuracy of 91.67%, a chance of achieving a complete remission, with a high discriminant ability (AUROC 0.9375).

Conclusion

Our solution allows an accurate assessment of complete remission achievement and monitoring of patients from the group with a lower probability of complete remission. The obtained models are scalable and can be improved by introducing new patient records.

Machine Learning for Diagnosis of Systemic Lupus Erythematosus: A Systematic Review and Meta-Analysis

Background

Application of machine learning (ML) for identification of systemic lupus erythematosus (SLE) has been recently drawing increasing attention, while there is still lack of evidence-based support.

Methods

Systematic review and meta-analysis are conducted to evaluate its diagnostic accuracy and application prospect. PubMed, Embase, Cochrane Library, and Web of Science libraries are searched, in combination with manual searching and literature retrospection, for studies regarding machine learning for identifying SLE and neuropsychiatric systemic lupus erythematosus (NPSLE). Quality Assessment of Diagnostic Accuracy Studies (QUADA-2) is applied to assess the quality of included studies. Diagnostic accuracy of the SLE model and NPSLE model is assessed using the bivariate fixed-effect model, and the data are pooled. Summary receiver operator characteristic curve (SROC) is plotted, and area under the curve (AUC) is calculated.

Results

Eighteen (18) studies are included, in which ten (10) focused on SLE and eight (8) on NPSLE. The AUC of SLE identification is 0.95, the sensitivity is 0.90, the specificity is 0.89, the PLR is 8.4, the NLR is 0.12, and the DOR is 73. AUC of NPSLE identification is 0.89, the sensitivity is 0.83, the specificity is 0.83, the PLR is 5.0, the NLR is 0.20, and the DOR is 25.

Conclusion

Machine learning presented remarkable performance in identification of SLE and NPSLE. Based on the convenience for inclusion factor collection and non-invasiveness of detection, machine learning is expected to be widely applied in clinical practice to assist medical decision making.

The performance of different classification criteria for systemic lupus erythematosus in a real-world rheumatology department

OBJECTIVE

New classification criteria have been proposed to improve classification of systemic lupus erythematosus (SLE). We aimed to evaluate their performance by determining their sensitivity, specificity and accuracy in a real-world rheumatology department.

METHODS

SLE patients who were enrolled in the Australian Lupus Registry and Biobank were included and compared with controls recruited from other rheumatology clinics. Clinical and immunological features were reviewed, according to ACR 1997, SLICC 2012, EULAR/ACR 2019, or Systemic Lupus Erythematosus Risk Probability Index (SLERPI). Performance of each set of criteria was evaluated for the overall cohort and in a subgroup of patients with early SLE.

RESULTS

The study included 394 SLE and 123 control patients with other rheumatological conditions. Sensitivity was highest using SLICC 2012 or SLERPI 2020 criteria. Specificity was highest using ACR 1997 criteria. The SLICC 2012 criteria had the highest overall accuracy at 94.4% (95% CI: 91.7, 97.1%). In the subgroup analysis of SLE patients with early disease, SLICC 2012 performed similarly well.

CONCLUSIONS

The sensitivity and specificity of each set of classification criteria vary slightly, with SLICC 2012 and SLERPI 2020 having the highest sensitivities and the ACR 1997 criteria having the highest specificity in our patient cohort. All classification criteria serve as good instructional aids for clinicians to understand SLE manifestations. For the Australian Lupus Registry and Biobank, we will continue to use the ACR 1997 and/or SLICC 2012 as entry to the observational cohort.

Narrative Review of Machine Learning in Rheumatic and Musculoskeletal Diseases for Clinicians and Researchers: Biases, Goals, and Future Directions

There has been rapid growth in the use of artificial intelligence (AI) analytics in medicine in recent years, including in rheumatic and musculoskeletal diseases (RMDs). Such methods represent a challenge to clinicians, patients, and researchers, given the "black box" nature of most algorithms, the unfamiliarity of the terms, and the lack of awareness of potential issues around these analyses. Therefore, this review aims to introduce this subject area in a way that is relevant and meaningful to clinicians and researchers. We hope to provide some insights into relevant strengths and limitations, reporting guidelines, as well as recent examples of such analyses in key areas, with a focus on lessons learned and future directions in diagnosis, phenotyping, prognosis, and precision medicine in RMDs.

Recent advances in the use of machine learning and artificial intelligence to improve diagnosis, predict flares, and enrich clinical trials in lupus

PURPOSE OF REVIEW

Machine learning is a computational tool that is increasingly used for the analysis of medical data and has provided the promise of more personalized care.

RECENT FINDINGS

The frequency with which machine learning analytics are reported in lupus research is comparable with that of rheumatoid arthritis and cancer, yet the clinical application of these computational tools has yet to be translated into better care. Considerable work has been applied to the development of machine learning models for lupus diagnosis, flare prediction, and classification of disease using histology or other medical images, yet few models have been tested in external datasets and independent centers. Application of machine learning has yet to be reported for lupus clinical trial enrichment and automated identification of eligible patients. Integration of machine learning into lupus clinical care and clinical trials would benefit from collaborative development between clinicians and data scientists.

SUMMARY

Although the application of machine learning to lupus data is at a nascent stage, initial results suggest a promising future.

Efficiency of Disease and Disease Activity Diagnosis Models of Systemic Lupus Erythematosus Based on Protein Array Analysis

Background

Systemic lupus erythematosus (SLE) has become increasingly common in the clinic and requires complicated evidence of both clinical manifestations and laboratory examinations. Additionally, the assessment and monitoring of lupus disease activity are challenging. We hope to find efficient biomarkers and establish diagnostic models of SLE.

Materials and Methods

We detected and quantified 40 proteins using a quantitative protein array of 76 SLE patients and 21 healthy controls, and differentially expressed proteins were screened out by volcano plot. Logistic regression analysis was used to recognize biomarkers that could be enrolled in the disease diagnosis model and disease activity diagnosis model, and a receiver operating characteristic (ROC) curve was drawn to evaluate the efficiency of the model. A nomogram was depicted for convenient and visualized application of our models in the clinic. Decision curves and clinical impact curves were also plotted to validate our models.

Results

The protein levels of TNF RII, BLC, TNF RI, MIP-1b, eotaxin, MIG, MCSF, IL-8, MCP-1, and IL-10 showed significant differences between patients with SLE and healthy controls. TNF RII and MIP-1b were included in the SLE diagnosis model with logistic regression analysis, and the value of the area under the ROC curve (AUC) was 0.914 (95% confidence interval (CI), 0.859-0.969). TNF RII, BLC, and MIP-1b were enrolled in the disease activity diagnosis model, and the AUC value was 0.823 (95% CI 0.729-0.916). Both of the models that we established showed high efficiency. Additionally, the three protein biomarkers contained in the disease activity distinguish model provided additional benefit to conventional biomarkers in predicting active lupus.

Conclusions

The disease diagnosis model and disease activity diagnosis model that we developed based on protein array chip results showed high efficiency in differentiating patients with SLE from healthy controls and recognizing SLE patients with high disease activity, and they have also been validated. This implied that they might greatly benefit clinical decisions and the treatment of SLE.

Big data analyses and individual health profiling in the arena of rheumatic and musculoskeletal diseases (RMDs)

Health care processes are under constant development and will need to embrace advances in technology and health science aiming to provide optimal care. Considering the perspective of increasing treatment options for people with rheumatic and musculoskeletal diseases, but in many cases not reaching all treatment targets that matter to patients, care systems bare potential to improve on a holistic level. This review provides an overview of systems and technologies under evaluation over the past years that show potential to impact diagnosis and treatment of rheumatic diseases in about 10 years from now. We summarize initiatives and studies from the field of electronic health records, biobanking, remote monitoring, and artificial intelligence. The combination and implementation of these opportunities in daily clinical care will be key for a new era in care of our patients. This aims to inform rheumatologists and healthcare providers concerned with chronic inflammatory musculoskeletal conditions about current important and promising developments in science that might substantially impact the management processes of rheumatic diseases in the 2030s.

Pre-Clinical Autoimmunity in Lupus Relatives: Self-Reported Questionnaires and Immune Dysregulation Distinguish Relatives Who Develop Incomplete or Classified Lupus From Clinically Unaffected Relatives and Unaffected, Unrelated Individuals

Systemic lupus erythematosus (SLE) is propelled by pathogenic autoantibody (AutoAb) and immune pathway dysregulation. Identifying populations at risk of reaching classified SLE is essential to curtail inflammatory damage. Lupus blood relatives (Rel) have an increased risk of developing SLE. We tested factors to identify Rel at risk of developing incomplete lupus (ILE) or classified SLE vs. clinically unaffected Rel and healthy controls (HC), drawing from two unique, well characterized lupus cohorts, the lupus autoimmunity in relatives (LAUREL) follow-up cohort, consisting of Rel meeting &lt;4 ACR criteria at baseline, and the Lupus Family Registry and Repository (LFRR), made up of SLE patients, lupus Rel, and HC. Medical record review determined ACR SLE classification criteria; study participants completed the SLE portion of the connective tissue disease questionnaire (SLE-CSQ), type 2 symptom questions, and provided samples for assessment of serum SLE-associated AutoAb specificities and 52 plasma immune mediators. Elevated SLE-CSQ scores were associated with type 2 symptoms, ACR scores, and serology in both cohorts. Fatigue at BL was associated with transition to classified SLE in the LAUREL cohort (p≤0.01). Increased levels of BLyS and decreased levels of IL-10 were associated with type 2 symptoms (p&lt;0.05). SLE-CSQ scores, ACR scores, and accumulated AutoAb specificities correlated with levels of multiple inflammatory immune mediators (p&lt;0.05), including BLyS, IL-2Rα, stem cell factor (SCF), soluble TNF receptors, and Th-1 type mediators and chemokines. Transition to SLE was associated with increased levels of SCF (p&lt;0.05). ILE Rel also had increased levels of TNF-α and IFN-γ, offset by increased levels of regulatory IL-10 and TGF-β (p&lt;0.05). Clinically unaffected Rel (vs. HC) had higher SLE-CSQ scores (p&lt;0.001), increased serology (p&lt;0.05), and increased inflammatory mediator levels, offset by increased IL-10 and TGF-β (p&lt;0.01). These findings suggest that Rel at highest risk of transitioning to classified SLE have increased inflammation coupled with decreased regulatory mediators. In contrast, clinically unaffected Rel and Rel with ILE demonstrate increased inflammation offset with increased immune regulation, intimating a window of opportunity for early intervention and enrollment in prevention trials.

Tailored treatment strategies and future directions in systemic lupus erythematosus

Systemic lupus erythematosus (SLE) represents a diagnostic and therapeutic challenge for physicians due to its protean manifestations and unpredictable course. The disease may manifest as multisystemic or organ-dominant and severity at presentation may vary according to age at onset (childhood-, adult- or late-onset SLE). Different manifestations may respond variably to different immunosuppressive medications and, even within the same organ-system, the severity of inflammation may vary from mild to organ-threatening. Current "state-of-the-art" in SLE treatment aims at remission or low disease activity in all organ systems. Apart from hydroxychloroquine and glucocorticoids (which should be used with caution), the choice of the appropriate immunosuppressive agent should be individualized and depend on the prevailing manifestation, severity stratification and patient childbearing potential. In this review, we provide an overview of therapeutic options for the various organ manifestations and severity patterns of the disease, different phenotypes (such as multisystem versus organ-dominant disease), as well as specific considerations, including lupus with antiphospholipid antibodies, childhood and late-onset disease, as well as treatment options during pregnancy and lactation.

Noise-immune Extreme Ensemble Learning for Early Diagnosis of Neuropsychiatric Systemic Lupus Erythematosus

Early diagnosis is currently the most effective way of saving the life of patients with neuropsychiatric systemic lupus erythematosus (NPSLE). However, it is rather difficult to detect this terrible disease at the early stage, due to the subtle and elusive symptomatic signals. Recent studies show that the ¹H-MRS (proton magnetic resonance spectroscopy) imaging technique can capture more information reflecting the early appearance of this disease than conventional magnetic resonance imaging techniques. 1H-MRS data, however, also presents more noises that can bring serious diagnosis bias. We hence proposed a noise-immune extreme ensemble learning technique for effectively leveraging 1H-MRS data for advancing the early diagnosis of NPSLE. Our main results are that 1) by developing generalized maximum correntropy criterion in the kernel extreme learning setting, many types of non-Gaussian noises can be distinguished, and 2) weighted recursive feature elimination, using maximal information coefficient to weight feature's importance, helps to further alleviate the bad impact of noises on the diagnosis performance. The proposed method is assessed on a publicly available dataset with 97.5% accuracy, 95.8% sensitivity, and 99.9% specificity, which well demonstrates its efficacy.

Performance of the systemic lupus erythematosus risk probability index in a cohort of undifferentiated connective tissue disease

OBJECTIVES

We sought to evaluate the performance of the systemic lupus erythematosus (SLE) Risk Probability Index (SLERPI) for identification of SLE in a large cohort of patients with undifferentiated connective tissue disease (UCTD).

METHODS

The SLERPI was applied in a cohort of patients who met classification criteria for UCTD and did not fulfill any classification criteria for other defined CTD including SLE. Patients with a SLERPI score of > 7 were "diagnosed" as SLE. Patients diagnosed with SLE and those not, were compared in terms of disease characteristics and index parameters.

RESULTS

A total of 422 patients with UCTD were included in the study. Median (IQR) SLERPI was 4.25 (2.5) points, while 39 (9.2%) patients had a SLERPI score >7 and were diagnosed as SLE. Patients with younger age (p = 0.026) and presence of malar rash (p < 0.0001), mucosal ulcer (p < 0.0001), alopecia (p < 0.0001), ANA positivity (p < 0.0001), low C3 and C4 (p = 0.002), proteinuria>500 mg/24 hours (p = 0.001), thrombocytopenia (p = 0.009) or autoimmune haemolytic anaemia (p < 0.0001) were more likely to fulfill criteria for SLE by the SLERPI.

CONCLUSION

SLERPI enabled a significant proportion of patients to be identified as SLE in our UCTD cohort. This new probability index may be useful for early identification of SLE among patients with signs of CTD without fulfilling any definite criteria set.

Risiko-Wahrscheinlichkeits-Index zur Diagnose eines Lupus erythematodes

Einen systemischen Lupus erythematodes (SLE) zu diagnostizieren kann sich mitunter über Monate oder sogar Jahre hinziehen. Selbst die inzwischen verbesserten Diagnosekriterien der Fachgesellschaften konnten die Diagnosestellung, gerade in den frühen Erkrankungsstadien, nicht erleichtern. Mit dem von Adamichou und ihren Kollegen entwickelten Modell kann ein SLE hingegen mit hoher Genauigkeit detektiert werden.

Cardiovascular risk assessment using ASCVD risk score in fibromyalgia: a single-centre, retrospective study using "traditional" case control methodology and "novel" machine learning

BACKGROUND

In autoimmune inflammatory rheumatological diseases, routine cardiovascular risk assessment is becoming more important. As an increased cardiovascular disease (CVD) risk is recognized in patients with fibromyalgia (FM), a combination of traditional CVD risk assessment tool with Machine Learning (ML) predictive model could help to identify non-traditional CVD risk factors.

METHODS

This study was a retrospective case-control study conducted at a quaternary care center in India. Female patients diagnosed with FM as per 2016 modified American College of Rheumatology 2010/2011 diagnostic criteria were enrolled; healthy age and gender-matched controls were obtained from Non-communicable disease Initiatives and Research at AMrita (NIRAM) study database. Firstly, FM cases and healthy controls were age-stratified into three categories of 18-39 years, 40-59 years, and ≥ 60 years. A 10 year and lifetime CVD risk was calculated in both cases and controls using the ASCVD calculator. Pearson chi-square test and Fisher's exact were used to compare the ASCVD risk scores of FM patients and controls across the age categories. Secondly, ML predictive models of CVD risk in FM patients were developed. A random forest algorithm was used to develop the predictive models with ASCVD 10 years and lifetime risk as target measures. Model predictive accuracy of the ML models was assessed by accuracy, f1-score, and Area Under 'receiver operating Curve' (AUC). From the final predictive models, we assessed risk factors that had the highest weightage for CVD risk in FM.

RESULTS

A total of 139 FM cases and 1820 controls were enrolled in the study. FM patients in the age group 40-59 years had increased lifetime CVD risk compared to the control group (OR = 1.56, p = 0.043). However, CVD risk was not associated with FM disease severity and disease duration as per the conventional statistical analysis. ML model for 10-year ASCVD risk had an accuracy of 95% with an f1-score of 0.67 and AUC of 0.825. ML model for the lifetime ASCVD risk had an accuracy of 72% with an f1-score of 0.79 and AUC of 0.713. In addition to the traditional risk factors for CVD, FM disease severity parameters were important contributors in the ML predictive models.

CONCLUSION

FM patients of the 40-59 years age group had increased lifetime CVD risk in our study. Although FM disease severity was not associated with high CVD risk as per the conventional statistical analysis of the data, it was among the highest contributor to ML predictive model for CVD risk in FM patients. This also highlights that ML can potentially help to bridge the gap of non-linear risk factor identification.

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.

Digital health, big data and smart technologies for the care of patients with systemic autoimmune diseases: Where do we stand?

The past decade has seen tremendous development in digital health, including in innovative new technologies such as Electronic Health Records, telemedicine, virtual visits, wearable technology and sophisticated analytical tools such as artificial intelligence (AI) and machine learning for the deep-integration of big data. In the field of rare connective tissue diseases (rCTDs), these opportunities include increased access to scarce and remote expertise, improved patient monitoring, increased participation and therapeutic adherence, better patient outcomes and patient empowerment. In this review, we discuss opportunities and key-barriers to improve application of digital health technologies in the field of autoimmune diseases. We also describe what could be the fully digital pathway of rCTD patients. Smart technologies can be used to provide real-world evidence about the natural history of rCTDs, to determine real-life drug utilization, advanced efficacy and safety data for rare diseases and highlight significant unmet needs. Yet, digitalization remains one of the most challenging issues faced by rCTD patients, their physicians and healthcare systems. Digital health technologies offer enormous potential to improve autoimmune rCTD care but this potential has so far been largely unrealized due to those significant obstacles. The need for robust assessments of the efficacy, affordability and scalability of AI in the context of digital health is crucial to improve the care of patients with rare autoimmune diseases.