Machine Learning for Prediction and Risk Stratification of Lupus Nephritis Renal Flare

Development and validation of a prediction model for coronary heart disease risk in depressed patients aged 20 years and older using machine learning algorithms

Background

Depression is being increasingly acknowledged as an important risk factor contributing to coronary heart disease (CHD). Currently, there is no predictive model specifically designed to evaluate the risk of coronary heart disease among individuals with depression. We aim to develop a machine learning (ML) model that will analyze risk factors and forecast the probability of coronary heart disease in individuals suffering from depression.

Methods

This research employed data from the National Health and Nutrition Examination Survey (NHANES) from 2007-2018, which included 2,085 individuals who had previously been diagnosed with depression. The population was randomly divided into a training set and a validation set, with an 8:2 ratio. Univariate and multivariate logistic regression analyses were employed to identify independent risk factors for coronary heart disease in individuals with depression. Eight machine learning algorithms were applied to the training set to construct the model, including logistic regression (LR), random forest (RF), gradient boosting machine (GBM), support vector machine (SVM), extreme gradient boosting (XGBoost), classification and regression tree (CART), k-nearest neighbors (KNN), and neural network (NNET). The validation set are used to evaluate the various performances of eight machine learning models. Several evaluation metrics were employed to assess and compare the performance of eight different machine learning models, aiming to identify the most effective algorithm for predicting coronary heart disease risk in individuals with depression. The evaluation metrics applied in this study included the area under the receiver operating characteristic (ROC) curve, calibration curve, Brier scores, decision curve analysis (DCA), and the precision-recall (PR) curve. And internally validated by the bootstrap method.

Results

Univariate and multivariate logistic regression analyses identified age, chest pain status, history of myocardial infarction, serum triglyceride levels, and education level as independent predictors of coronary heart disease risk. Eight machine learning algorithms are applied to construct the models, among which the Random Forest model has the best performance, with an (Area Under Curve) AUC of 0.987 for the random forest model in the training set, and an AUC of 0.848 for the PR curve. In the validation set, the random forest model achieves an AUC of 0.996, and an AUC of 0.960 for the PR curve, which demonstrates an excellent discriminative ability. Calibration curves indicated high congruence between observed and predicted odds, with minimal Brier scores of 0.026 and 0.021 for the training, respectively, reinforcing the model's ability to discriminate. Set and validation set, respectively, reinforcing the model's predictive accuracy. DCA curves confirmed net benefits of the random forest model across. Furthermore, the AUC of the random forest model was 0.928 after internal validation by bootstrap method, indicating that its discriminative ability is good, and the model is useful for clinical assessment of the risk of coronary heart disease in depressed people.

Conclusion

The random forest algorithm exhibited the best predictive performance, potentially aiding clinicians in assessing the risk probabilities of coronary heart disease within this population.

Diagnostic model of microvasculature and neurologic alterations in the retina and optic disc for lupus nephritis

BACKGROUND

Machine learning (ML) analysis of retinal nerve fiber layer (RNFL) thickness and vessel density (VD) alterations in the macular region and optic disc may provide a new diagnostic method for lupus nephritis (LN). This study aimed to assess these alterations in LN patients using optical coherence tomography angiography (OCTA).

METHODS

A retrospective analysis was conducted on 81 systemic lupus erythematosus (SLE) patients without retinopathy, divided into two groups: LN (41 patients) and non-LN (39 patients). OCTA imaging was performed on all participants. Independent risk factors were identified through univariate and multivariate analyses, followed by the development of a random forest (RF) diagnostic model.

RESULTS

A total of 37 RNFL and VD variables from the macular region and 23 from the optic disc were analyzed. Through elastic net regression, 16 significant factors were identified. Further multivariate logistic regression selected 8 critical factors, which were used to construct the RF model. The RF model achieved an area under the curve (AUC) of 0.950 (95 % CI: 0.882 to 1.000), accuracy of 0.903 (95 % CI: 0.743 to 0.980), sensitivity of 0.867, specificity of 0.938, a positive predictive value (PPV) of 0.929, and a negative predictive value (NPV) of 0.882.

CONCLUSION

This study highlights the potential of ML-based OCTA data in diagnosing LN. Key diagnostic factors included perimeter (PERIM), superficial capillary plexus vessel density (SVD) - parafoveal (para)-temporal (T), SVD-perifoveal (peri)-inferior (I), RNFL-Fovea, RNFL-Peri, RNFL-Peri-T, capillary-whole-image, and peripapillary RNFL (PRNFL)- inferonasal (IN).

Interferon-α as a biomarker to predict renal outcomes in lupus nephritis

OBJECTIVE

To determine if serum interferon (IFN)-α levels at the time of a lupus nephritis (LN) flare are associated with renal outcomes.

METHODS

Patients with an LN flare who had a preflare estimated glomerular filtration rate (eGFR) ≥60 mL/min were included in the study. The following outcomes were ascertained: (1) Time to first and second LN flares during follow-up, (2) Time to a sustained decline in eGFR by 30% and 50%, and progression to end-stage renal disease (ESRD, <15 mL/min), and (3) Time to an adverse renal event (≥2 renal flares and/or at least a 30% sustained decline in eGFR during follow-up). Serum IFN-α was measured by Simoa.

RESULTS

92 patients with active LN were included in the study. Elevated serum baseline levels of IFN-α predicted poor renal outcomes. Patients with higher baseline IFN-α had a greater risk of having two or more subsequent LN flares (HR: 1.31 (1.08-1.59), p=0.006), sustained 30% decline in eGFR (HR: 1.27 (1.14-1.40), p<0.001), 50% decline in eGFR (HR: 1.27 (1.12-1.33), p<0.001) and progressing to ESRD (HR: 1.29 (1.14-1.47), p<0.001). Receiver operating characteristic analysis identified an IFN-α cut-off, 0.6 pg/ml, for predicting an adverse renal event.

CONCLUSIONS

Elevated serum IFN-α levels measured at the time of an LN flare are associated with poor renal outcomes, including the development of ≥2 LN flares, and a clinically meaningful decline in kidney function.

Predicting autoimmune diseases: A comprehensive review of classic biomarkers and advances in artificial intelligence

Autoimmune diseases comprise a spectrum of disorders characterized by the dysregulation of immune tolerance, resulting in tissue or organ damage and inflammation. Their prevalence has been on the rise, significantly impacting patients' quality of life and escalating healthcare costs. Consequently, the prediction of autoimmune diseases has recently garnered substantial interest among researchers. Despite their wide heterogeneity, many autoimmune diseases exhibit a consistent pattern of paraclinical findings that hold predictive value. From serum biomarkers to various machine learning approaches, the array of available methods has been continuously expanding. The emergence of artificial intelligence (AI) presents an exciting new range of possibilities, with notable advancements already underway. The ultimate objective should revolve around disease prevention across all levels. This review provides a comprehensive summary of the most recent data pertaining to the prediction of diverse autoimmune diseases and encompasses both traditional biomarkers and the latest innovations in AI.

Lupus Nephritis from Pathogenesis to New Therapies: An Update

Lupus Nephritis (LN) still represents one of the most severe complications of Systemic Lupus Erythematosus (SLE) and a major risk factor for morbidity and mortality. However, over the last few years, several studies have paved the way for a deeper understanding of its pathogenetic mechanisms and more targeted treatments. This review aims to provide a comprehensive update on progress on several key aspects in this setting: pathogenetic mechanisms of LN, including new insight into the role of autoantibodies, complement, vitamin D deficiency, and interaction between infiltrating immune cells and kidney resident ones; the evolving role of renal biopsy and biomarkers, which may integrate information from renal histology; newly approved drugs such as voclosporin (VOC) and belimumab (BEL), allowing a more articulate strategy for induction therapy, and other promising phase III-immunosuppressive (IS) agents in the pipeline. Several adjunctive treatments aimed at reducing cardiovascular risk and progression of chronic renal damage, such as antiproteinuric agents, represent an important complement to IS therapy. Furthermore, non-pharmacological measures concerning general lifestyle and diet should also be adopted when managing LN. Integrating these therapeutic areas requires an effort towards a holistic and multidisciplinary approach. At the same time, the availability of an increasingly wider armamentarium may translate into improvements in patient's renal outcomes over the next decades.

Ensemble machine learning prediction of hyperuricemia based on a prospective health checkup population

Objectives: An accurate prediction model for hyperuricemia (HUA) in adults remain unavailable. This study aimed to develop a stacking ensemble prediction model for HUA to identify high-risk groups and explore risk factors. Methods: A prospective health checkup cohort of 40899 subjects was examined and randomly divided into the training and validation sets with the ratio of 7:3. LASSO regression was employed to screen out important features and then the ROSE sampling was used to handle the imbalanced classes. An ensemble model using stacking strategy was constructed based on three individual models, including support vector machine, decision tree C5.0, and eXtreme gradient boosting. Model validations were conducted using the area under the receiver operating characteristic curve (AUC) and the calibration curve, as well as metrics including accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score. A model agnostic instance level variable attributions technique (iBreakdown) was used to illustrate the black-box nature of our ensemble model, and to identify contributing risk factors. Results: Fifteen important features were screened out of 23 clinical variables. Our stacking ensemble model with an AUC of 0.854, outperformed the other three models, support vector machine, decision tree C5.0, and eXtreme gradient boosting with AUCs of 0.848, 0.851 and 0.849 respectively. Calibration accuracy as well as other metrics including accuracy, specificity, negative predictive value, and F1 score were also proved our ensemble model's superiority. The contributing risk factors were estimated using six randomly selected subjects, which showed that being female and relatively younger, together with having higher baseline uric acid, body mass index, γ-glutamyl transpeptidase, total protein, triglycerides, creatinine, and fasting blood glucose can increase the risk of HUA. To further validate our model's applicability in the health checkup population, we used another cohort of 8559 subjects that also showed our ensemble prediction model had favorable performances with an AUC of 0.846. Conclusion: In this study, the stacking ensemble prediction model for HUA was developed, and it outperformed three individual models that compose it (support vector machine, decision tree C5.0, and eXtreme gradient boosting). The contributing risk factors were identified with insightful ideas.

Deep learning model to predict lupus nephritis renal flare based on dynamic multivariable time-series data

OBJECTIVES

To develop an interpretable deep learning model of lupus nephritis (LN) relapse prediction based on dynamic multivariable time-series data.

DESIGN

A single-centre, retrospective cohort study in China.

SETTING

A Chinese central tertiary hospital.

PARTICIPANTS

The cohort study consisted of 1694 LN patients who had been registered in the Nanjing Glomerulonephritis Registry at the National Clinical Research Center of Kidney Diseases, Jinling Hospital from January 1985 to December 2010.

METHODS

We developed a deep learning algorithm to predict LN relapse that consists of 59 features, including demographic, clinical, immunological, pathological and therapeutic characteristics that were collected for baseline analysis. A total of 32 227 data points were collected by the sliding window method and randomly divided into training (80%), validation (10%) and testing sets (10%). We developed a deep learning algorithm-based interpretable multivariable long short-term memory model for LN relapse risk prediction considering censored time-series data based on a cohort of 1694 LN patients. A mixture attention mechanism was deployed to capture variable interactions at different time points for estimating the temporal importance of the variables. Model performance was assessed according to C-index (concordance index).

RESULTS

The median follow-up time since remission was 4.1 (IQR, 1.7-6.7) years. The interpretable deep learning model based on dynamic multivariable time-series data achieved the best performance, with a C-index of 0.897, among models using only variables at the point of remission or time-variant variables. The importance of urinary protein, serum albumin and serum C3 showed time dependency in the model, that is, their contributions to the risk prediction increased over time.

CONCLUSIONS

Deep learning algorithms can effectively learn through time-series data to develop a predictive model for LN relapse. The model provides accurate predictions of LN relapse for different renal disease stages, which could be used in clinical practice to guide physicians on the management of LN patients.

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.

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.

Which extra-renal flare is 'difficult to treat' in systemic lupus erythematosus? A one-year longitudinal study comparing traditional and machine learning approaches

OBJECTIVES

To describe phenotypes and outcomes of extra-renal flares in SLE, to identify clusters of extra-renal flares based on baseline features, and to develop a machine learning (ML) tool capable of predicting 'difficult to treat' (D2T) flares.

METHODS

Extra-renal flares that occurred in our cohort over the last five years with at least one year of follow-up were included. Baseline clinical variables were described and flares assigned to clusters. Attainment of remission and low disease activity state (LLDAS) at 12 months were compared. Flares were then considered 'D2T' in case of non-attainment of LLDAS at 6 and 12 months. Baseline features were used to train a ML model able to predict future D2T-flares, at admission. Traditional approaches were then compared with informatic techniques.

RESULTS

Among 420 SLE patients of the cohort, 114 flares occurred between 2015 and 2021; 79 extra-renal flares, predominantly mucocutaneous (24.1%) and musculoskeletal (45.6%), were considered. After 12 months, 79.4% and 49.4% were in LLDAS and in remission, respectively, while 17 flares were classified as D2T (21.5%); D2T flares received a higher cumulative and daily dose of glucocorticoids. Among the clusters, cluster 'D' (mild-moderate flares with mucocutaneous manifestations in patients with history of skin involvement) was associated with the lowest rate of remission. Among clinical data, not being on LLDAS at 3 months was the unique independent predictor of D2T flares.

CONCLUSIONS

Our clusterization well separates extra-renal flares according to their baseline features and may propose a new identification standard. D2T flares, especially refractory skin manifestations, are frequent in SLE and represent an unmet need in the management of the disease as they are associated with higher glucocorticoid (GC) dosage and risk of damage accrual. Our ML model could help in the early identification of D2T flares, flagging them to elevate the attention threshold at admission.

Development and validation of a prognostic nomogram for the renal relapse of lupus nephritis

OBJECTIVES

This study aims to assess the risk of relapse after complete remission (CR) and partial remission (PR), and to develop a prognostic nomogram predicting the probability in lupus nephritis (LN) patients.

METHODS

Data from patients with LN who had been in remission were collected as a training cohort. The prognostic factors were analyzed using the univariable and multivariable Cox model for the training group. A nomogram was then developed using significant predictors in multivariable analysis. Both discrimination and calibration were assessed by bootstrapping with 100 resamples.

RESULTS

A total of 247 participants were enrolled, including 108 in the relapse group and 139 in the no relapse group. In multivariate Cox analysis, Systemic Lupus Erythematosus Disease Activity Index (SLEDAI), erythrocyte sedimentation rate (ESR), complement 1q (C1q), and antiphospholipid (aPL), anti-Sm antibody were found to be significant for predicting relapse rates. The prognostic nomogram including the aforementioned factors effectively predicted 1- and 3-year probability of flare-free. Moreover, a favorable consistency between the predicted and actual survival probabilities was demonstrated using calibration curves.

CONCLUSIONS

High SLEDAI, ESR, and positive aPL, anti-Sm antibody are potential risk factors for LN flare, while high C1q can reduce its recurrence. The visualized model we established can help predict the relapse risk of LN and aid clinical decision-making for individual patients.

Flares in Lupus Nephritis: Risk Factors and Strategies for Their Prevention

PURPOSE OF REVIEW

Discuss the prognostic significance of kidney flares in patients with lupus nephritis, associated risk factors, and possible preventative strategies.

RECENT FINDINGS

Recently performed clinical trials and observational cohort studies underscore the high frequency of relapses of kidney disease, following initial response, in patients with proliferative and/or membranous lupus nephritis. Analysis of hard disease outcomes such as progression to chronic kidney disease or end-stage kidney disease, coupled with histological findings from repeat kidney biopsy studies, have drawn attention to the importance of renal function preservation that should be pursued as early as lupus nephritis is diagnosed. In this respect, non-randomized and randomized evidence have suggested a number of factors associated with reduced risk of renal flares such as attaining a very low level of proteinuria (< 700-800 mg/24 h by 12 months), using mycophenolate over azathioprine, adding belimumab to standard therapy, maintaining immunosuppressive/biological treatment for at least 3 to 5 years, and using hydroxychloroquine. Other factors that warrant further clarification include serological activity and the use of repeat kidney biopsy to guide the intensity and duration of treatment in selected cases. The results from ongoing innovative studies integrating kidney histological and clinical outcomes, together with an expanding spectrum of therapies in lupus nephritis, are expected to facilitate individual medical care and long-term disease and patient prognosis.

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.

Complement as a Biomarker for Systemic Lupus Erythematosus

Systemic lupus erythematosus (SLE) is a disease of immune complex deposition; therefore, complement plays a vital role in the pathogenesis of SLE. In general, complement levels in blood and complement deposition in histological tests are used for the management of SLE. Thus, the evaluation of complement status can be useful in the diagnosis of SLE, assessment of disease activity, and prediction of treatment response and prognosis. In addition, novel complement biomarkers, such as split products and cell-bound complement activation products, are considered to be more sensitive than traditional complement markers, such as serum C3 and C4 levels and total complement activity (CH50), which become more widely used. In this review, we report the complement testing in the management of SLE over the last decade and summarize their utility.

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).

Novel aspects in the pathophysiology and diagnosis of glomerular diseases

Immune deposits/complexes are detected in a multitude of tissues in autoimmune disorders, but no organ has attracted as much attention as the kidney. Several kidney diseases are characterised by the presence of specific configurations of such deposits, and many of them are under a 'shared care' between rheumatologists and nephrologists. This review focuses on five different diseases commonly encountered in rheumatological and nephrological practice, namely IgA vasculitis, lupus nephritis, cryoglobulinaemia, anti-glomerular basement membrane disease and anti-neutrophil cytoplasm-antibody glomerulonephritis. They differ in disease aetiopathogenesis, but also the potential speed of kidney function decline, the responsiveness to immunosuppression/immunomodulation and the deposition of immune deposits/complexes. To date, it remains unclear if deposits are causing a specific disease or aim to abrogate inflammatory cascades responsible for tissue damage, such as neutrophil extracellular traps or the complement system. In principle, immunosuppressive therapies have not been developed to tackle immune deposits/complexes, and repeated kidney biopsy studies found persistence of deposits despite reduction of active inflammation, again highlighting the uncertainty about their involvement in tissue damage. In these studies, a progression of active lesions to chronic changes such as glomerulosclerosis was frequently reported. Novel therapeutic approaches aim to mitigate these changes more efficiently and rapidly. Several new agents, such as avacopan, an oral C5aR1 inhibitor, or imlifidase, that dissolves IgG within minutes, are more specifically reducing inflammatory cascades in the kidney and repeat tissue sampling might help to understand their impact on immune cell deposition and finally kidney function recovery and potential impact of immune complexes/deposits.

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.

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.

Development and internal validation of a risk model for hyperuricemia in diabetic kidney disease patients

Purpose

This research aimed to identify independent risk factors for hyperuricemia (HUA) in diabetic kidney disease (DKD) patients and develop an HUA risk model based on a retrospective study in Ningbo, China.

Patients and methods

Six hundred and ten DKD patients attending the two hospitals between January 2019 and December 2020 were enrolled in this research and randomized to the training and validation cohorts based on the corresponding ratio (7:3). Independent risk factors associated with HUA were identified by multivariable logistic regression analysis. The characteristic variables of the HUA risk prediction model were screened out by the least absolute shrinkage and selection operator (LASSO) combined with 10-fold cross-validation, and the model was presented by nomogram. The C-index and receiver operating characteristic (ROC) curve, calibration curve and Hosmer-Lemeshow test, and decision curve analysis (DCA) were performed to evaluate the discriminatory power, degree of fitting, and clinical applicability of the risk model.

Results

Body mass index (BMI), HbA1c, estimated glomerular filtration rate (eGFR), and hyperlipidemia were identified as independent risk factors for HUA in the DKD population. The characteristic variables (gender, family history of T2DM, drinking history, BMI, and hyperlipidemia) were screened out by LASSO combined with 10-fold cross-validation and included as predictors in the HUA risk prediction model. In the training cohort, the HUA risk model showed good discriminatory power with a C-index of 0.761 (95% CI: 0.712-0.810) and excellent degree of fit (Hosmer-Lemeshow test, P > 0.05), and the results of the DCA showed that the prediction model could be beneficial for patients when the threshold probability was 9-79%. Meanwhile, the risk model was also well validated in the validation cohort, where the C-index was 0.843 (95% CI: 0.780-0.906), the degree of fit was good, and the DCA risk threshold probability was 7-100%.

Conclusion

The development of risk models contributes to the early identification and prevention of HUA in the DKD population, which is vital for preventing and reducing adverse prognostic events in DKD.

Adverse pregnancy outcomes in women with systemic lupus erythematosus: can we improve predictions with machine learning?

OBJECTIVES

Nearly 20% of pregnancies in patients with SLE result in an adverse pregnancy outcome (APO). We previously developed an APO prediction model using logistic regression and data from Predictors of pRegnancy Outcome: bioMarkers In Antiphospholipid Antibody Syndrome and Systemic Lupus Erythematosus (PROMISSE), a large multicentre study of pregnant women with mild/moderate SLE and/or antiphospholipid antibodies. Our goal was to determine whether machine learning (ML) approaches improve APO prediction and identify other risk factors.

METHODS

The PROMISSE data included 41 predictors from 385 subjects; 18.4% had APO (preterm delivery due to placental insufficiency/pre-eclampsia, fetal/neonatal death, fetal growth restriction). Logistic regression with stepwise selection (LR-S), least absolute shrinkage and selection operator (LASSO), random forest (RF), neural network (NN), support vector machines (SVM-RBF), gradient boosting (GB) and SuperLearner (SL) were compared by cross-validated area under the ROC curve (AUC) and calibration.

RESULTS

Previously identified APO risk factors, antihypertensive medication use, low platelets, SLE disease activity and lupus anticoagulant (LAC), were confirmed as important with each algorithm. LASSO additionally revealed potential interactions between LAC and anticardiolipin IgG, among others. SL performed the best (AUC=0.78), but was statistically indistinguishable from LASSO, SVM-RBF and RF (AUC=0.77 for all). LR-S, NN and GB had worse AUC (0.71-0.74) and calibration scores.

CONCLUSIONS

We predicted APO with reasonable accuracy using variables routinely assessed prior to the 12th week of pregnancy. LASSO and some ML methods performed better than a standard logistic regression approach. Substantial improvement in APO prediction will likely be realised, not with increasingly complex algorithms but by the discovery of new biomarkers and APO risk factors.

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.

Artificial Intelligence-Assisted Renal Pathology: Advances and Prospects

Digital imaging and advanced microscopy play a pivotal role in the diagnosis of kidney diseases. In recent years, great achievements have been made in digital imaging, providing novel approaches for precise quantitative assessments of nephropathology and relieving burdens of renal pathologists. Developing novel methods of artificial intelligence (AI)-assisted technology through multidisciplinary interaction among computer engineers, renal specialists, and nephropathologists could prove beneficial for renal pathology diagnoses. An increasing number of publications has demonstrated the rapid growth of AI-based technology in nephrology. In this review, we offer an overview of AI-assisted renal pathology, including AI concepts and the workflow of processing digital image data, focusing on the impressive advances of AI application in disease-specific backgrounds. In particular, this review describes the applied computer vision algorithms for the segmentation of kidney structures, diagnosis of specific pathological changes, and prognosis prediction based on images. Lastly, we discuss challenges and prospects to provide an objective view of this topic.

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.

Artificial intelligence-enabled decision support in nephrology

Kidney pathophysiology is often complex, nonlinear and heterogeneous, which limits the utility of hypothetical-deductive reasoning and linear, statistical approaches to diagnosis and treatment. Emerging evidence suggests that artificial intelligence (AI)-enabled decision support systems - which use algorithms based on learned examples - may have an important role in nephrology. Contemporary AI applications can accurately predict the onset of acute kidney injury before notable biochemical changes occur; can identify modifiable risk factors for chronic kidney disease onset and progression; can match or exceed human accuracy in recognizing renal tumours on imaging studies; and may augment prognostication and decision-making following renal transplantation. Future AI applications have the potential to make real-time, continuous recommendations for discrete actions and yield the greatest probability of achieving optimal kidney health outcomes. Realizing the clinical integration of AI applications will require cooperative, multidisciplinary commitment to ensure algorithm fairness, overcome barriers to clinical implementation, and build an AI-competent workforce. AI-enabled decision support should preserve the pre-eminence of wisdom and augment rather than replace human decision-making. By anchoring intuition with objective predictions and classifications, this approach should favour clinician intuition when it is honed by experience.

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.

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.