Tubular biomarkers and histology in lupus nephritis.

INTRODUCTION: The relevance of tubulo-interstitial involvement for kidney prognosis has recently been emphasized, but validated biomarkers for predicting histology are still lacking. The aim of our study was to evaluate different serum and urinary markers of tubular damage in patients with lupus nephritis (LN) and to correlate them with kidney histopathology. METHODS: A single-center retrospective study was conducted from January 2016 to December 2021. Serum and urine samples were collected on the same day of kidney biopsy and correlated with histologic data from a cohort of 15 LN patients. We analyzed the following urinary markers, adjusted for urine creatinine: beta 2-microglobulin, alpha 1-microglobulin, NGAL, uKIM-1, MCP-1, uDKK-3, and uUMOD. The serum markers sKIM-1 and sUMOD were also analyzed. RESULTS: A positive and strong correlation was observed between the degree of interstitial fibrosis (rho = 0.785, p = .001) and tubular atrophy (rho = 0.781, p = .001) and the levels of uDKK3. uUMOD also showed an inverse and moderate correlation with interstitial fibrosis (rho = -0.562, p = .037) and tubular atrophy (rho = -0.694, p = .006). Patients with >10% cortical interstitial inflammation had higher levels of uKIM-1 [4.9 (3.9, 5.5) vs. 0.8 (0.6, 1.5) mcg/mg, p = .001], MCP-1 [3.8 (2. 3, 4.2) vs. 0.7 (0.3, 1.2) mcg/mg, p = .001], sKIM-1 [9.2 (5.9, 32.7) vs. 1.4 (0, 3.5) pg/mL, p = .001], and lower sUMOD [8.7 (0, 39.7) vs. 46.1 (35.7, 53) ng/mL, p = .028]. CONCLUSION: The use of specific urinary and serum biomarkers of tubular dysfunction or injury may help to predict certain histologic parameters in LN patients.

[NETosis in lupus nephritis].

AIM: To evaluate the levels of MPO-DNA complex in patients with systemic lupus erythematosus (SLE) and its association with the presence of lupus nephritis (LN). MATERIALS AND METHODS: The study included 77 patients with SLE, of whom 30 had SLE without anti phospholipid syndrome (APS), 47 had SLE with APS, and 20 were healthy individuals serving as the control group. The MPO-DNA complex in the serum was investigated using ELISA. RESULTS: The levels of MPO-DNA complex in serum were significantly higher in patients with SLE compared to healthy controls (p=0.001). Among the patients with SLE, 30 (39%) had elevated levels of MPO-DNA complex. The presence of elevated MPO-DNA complex was significantly associated with the presence of a history of LN (p=0.009). Moreover, among the patients included in the study, 20 had active LN, and patients with elevated MPO-DNA complex levels were more likely to have active LN than patients without elevated MPO-DNA complex concentrations [12 (40%) of 30 vs 8 (17%) of 47, χ2=5.029; p=0.034]. An association was found between elevated levels of MPO-DNA complex and the presence of proteinuria, hematuria, cellular hematic/granular casts and aseptic leukocyturia. A direct correlation of MPO-DNA complex with SLEDAI-R was found in patients with active LN (rs=0.497; p=0.026). CONCLUSION: Elevated levels of MPO-DNA complex were detected in 39% of patients with SLE. These patients had a higher prevalence of LN in their medical history and at the time of inclusion in the study. The correlation between MPO-DNA complex levels and the activity of LN according to SLEDAI-R indicates the potential role of MPO-DNA complex as a biomarker for assessing the activity of renal damage in SLE.

Development and validation of a risk scoring system to identify patients with lupus nephritis in electronic health record data.

OBJECTIVE: Accurate identification of lupus nephritis (LN) cases is essential for patient management, research and public health initiatives. However, LN diagnosis codes in electronic health records (EHRs) are underused, hindering efficient identification. We investigated the current performance of International Classification of Diseases (ICD) codes, 9th and 10th editions (ICD9/10), for identifying prevalent LN, and developed scoring systems to increase identification of LN that are adaptable to settings with and without LN ICD codes. METHODS: Training and test sets derived from EHR data from a large health system. An external set comprised data from the EHR of a second large health system. Adults with ICD9/10 codes for SLE were included. LN cases were ascertained through manual chart reviews conducted by rheumatologists. Two definitions of LN were used: strict (definite LN) and inclusive (definite, potential or diagnostic uncertainty). Gradient boosting models including structured EHR fields were used for predictor selection. Two logistic regression-based scoring systems were developed ('LN-Code' included LN ICD codes and 'LN-No Code' did not), calibrated and validated using standard performance metrics. RESULTS: A total of 4152 patients from University of California San Francisco Medical Center and 370 patients from Zuckerberg San Francisco General Hospital and Trauma Center met the eligibility criteria. Mean age was 50 years, 87% were female. LN diagnosis codes demonstrated low sensitivity (43-73%) but high specificity (92-97%). LN-Code achieved an area under the curve (AUC) of 0.93 and a sensitivity of 0.88 for identifying LN using the inclusive definition. LN-No Code reached an AUC of 0.91 and a sensitivity of 0.95 (0.97 for the strict definition). Both scoring systems had good external validity, calibration and performance across racial and ethnic groups. CONCLUSIONS: This study quantified the underutilisation of LN diagnosis codes in EHRs and introduced two adaptable scoring systems to enhance LN identification. Further validation in diverse healthcare settings is essential to ensure their broader applicability.

Healthcare resource utilization and costs in patients with a newly confirmed diagnosis of lupus nephritis in the United States over a 5-year follow-up period.

BACKGROUND: We aimed to describe healthcare resource utilization (HCRU) and healthcare costs in patients with newly confirmed lupus nephritis (LN) in the United States over a 5-year follow-up period. METHODS: This retrospective, longitudinal cohort study (GSK Study 214102) utilized administrative claims data to identify individuals with a newly confirmed diagnosis of LN between August 01, 2011, and July 31, 2018, based on LN-specific International Classification of Diseases diagnosis codes. Index was the date of first LN-related diagnosis code claim. HCRU, healthcare costs, and incidence of systemic lupus erythematosus (SLE) flares were reported annually among eligible patients with at least 5 years continuous enrollment post-index. RESULTS: Of 2,159 patients with a newly confirmed diagnosis of LN meeting inclusion and exclusion criteria, 335 had at least 5 years continuous enrollment post-index. HCRU was greatest in the first year post-LN diagnosis across all categories (inpatient admission, emergency room [ER] visits, ambulatory visits, and pharmacy use), and trended lower, though remained substantial, in the 5-year follow-up period. Among patients with LN and HCRU, the mean (standard deviation [SD]) number of ER visits and inpatient admissions were 3.7 (4.6) and 1.8 (1.5), respectively, in Year 1, which generally remained stable in Years 2-5; the mean (SD) number of ambulatory visits and pharmacy fills were 35.8 (25.1) and 62.9 (43.8), respectively, in Year 1, and remained similar for Years 2-5. Most patients (≥ 91.6%) had ≥ 1 SLE flare in each of the 5 years of follow-up. The proportion of patients who experienced a severe SLE flare was higher in Year 1 (31.6%) than subsequent years (14.3-18.5%). Total costs (medical and pharmacy; mean [SD]) were higher in Year 1 ($44,205 [71,532]) than subsequent years ($29,444 [52,310]-$32,222 [58,216]), driven mainly by inpatient admissions (Year 1: $21,181 [58,886]; subsequent years: $7,406 [23,331]-$9,389 [29,283]). CONCLUSIONS: Patients with a newly confirmed diagnosis of LN have substantial HCRU and healthcare costs, particularly in the year post-diagnosis, largely driven by inpatient costs. This highlights the need for improved disease management to prevent renal damage, improve patient outcomes, and reduce costs among patients with renal involvement.

Serum Uric Acid Combined with Homocysteine as a Predictive Biomarker of Lupus Nephritis.

Serum uric acid (UA) and homocysteine (Hcy) are potential biomarkers of systemic lupus erythematosus (SLE). In this study, the expressions of UA and Hcy in SLE patients and the predictive value of these two parameters for lupus nephritis (LN) were studied. A total of 476 SLE patients were recruited to this case-control study, of which 176 SLE patients diagnosed with LN and 300 without LN. Serum UA and Hcy levels were analyzed. Multivariate logistic regression analysis was used to evaluate the relationship between serum UA and Hcy and LN. The receiver operating characteristic (ROC) curves were used to predict the role of combination of serum UA and Hcy in LN. We found that serum UA and Hcy levels in SLE patients with LN were significantly higher than those in controls (p<0.05). Multivariate logistic regressions showed that serum UA (OR+=+1.003, 95+% CI: 1.001-1.006, p+=+0.003), apolipoprotein B (Apo B) (OR+=+21.361, 95+% CI: 2.312-195.373, p+=+0.007) and Hcy (OR+=+1.042, 95+% CI: 1.011-1.080, p+=+0.014) were independent markers of LN. Combined serum UA and Hcy revealed a better result (AUC+=+0.718, 95+% CI: 0.670-0.676, p<0.001) in prediction of LN compared to that of the serum UA (AUC+=+0.710) and Hcy (AUC+=+0.657) independently. In conclusion, serum UA and Hcy could be predictive biomarkers of LN, and joint detection of serum UA and Hcy might be useful in the clinical setting.

Navigating the diagnostic maze: A case presentation of C1q vasculitis mimicking hypocomplementemic urticarial vasculitis in a patient with systemic lupus erythematosus.

In rare instances, patients with SLE may exhibit atypical clinical manifestations, such as Hypocomplementemic Urticarial Vasculitis, which can pose diagnostic challenges. Here, we present a case report of a 28-year-old female with a history of SLE with lupus nephritis clase IV who developed HUV-like symptoms, ultimately leading to a diagnosis of C1q Vasculitis. This case underscores the importance of considering C1q Vasculitis in SLE patients presenting with HUV-like features and highlights Rituximab as a promising therapeutic option for managing this rare condition.

Urinary metabolomic profiling of a cohort of Colombian patients with systemic lupus erythematosus.

Systemic lupus erythematosus (SLE) is an autoimmune and multisystem disease with a high public health impact. Lupus nephritis (LN), commonly known as renal involvement in SLE, is associated with a poorer prognosis and increased rates of morbidity and mortality in patients with SLE. Identifying new urinary biomarkers that can be used for LN prognosis or diagnosis is essential and is part of current active research. In this study, we applied an untargeted metabolomics approach involving liquid and gas chromatography coupled with mass spectrometry to urine samples collected from 17 individuals with SLE and no kidney damage, 23 individuals with LN, and 10 clinically healthy controls (HCs) to identify differential metabolic profiles for SLE and LN. The data analysis revealed a differentially abundant metabolite expression profile for each study group, and those metabolites may act as potential differential biomarkers of SLE and LN. The differential metabolic pathways found between the LN and SLE patients with no kidney involvement included primary bile acid biosynthesis, branched-chain amino acid synthesis and degradation, pantothenate and coenzyme A biosynthesis, lysine degradation, and tryptophan metabolism. Receiver operating characteristic curve analysis revealed that monopalmitin, glycolic acid, and glutamic acid allowed for the differentiation of individuals with SLE and no kidney involvement and individuals with LN considering high confidence levels. While the results offer promise, it is important to recognize the significant influence of medications and other external factors on metabolomics studies. This impact has the potential to obscure differences in metabolic profiles, presenting a considerable challenge in the identification of disease biomarkers. Therefore, experimental validation should be conducted with a larger sample size to explore the diagnostic potential of the metabolites found as well as to examine how treatment and disease activity influence the identified chemical compounds. This will be crucial for refining the accuracy and effectiveness of using urine metabolomics for diagnosing and monitoring lupus and lupus nephritis.

Clinicopathological correlation of patients with lupus nephritis: Data from a tertiary center in Saudi Arabia.

Systemic lupus erythematosus mainly affects young women, and approximately half of systemic lupus erythematosus patients develop lupus nephritis (LN). However, data on the types and remission rates of LN in Saudi Arabia are limited. Therefore, we aimed to highlight the LN remission rates in our population. A retrospective record review was conducted between January 2007 and December 2020 in a tertiary center in the western region of Saudi Arabia to determine the remission rates among patients with biopsy-proven LN who met the EULAR\ACR 2019 classification criteria. We identified 59 patients with biopsy-proven LN, mostly in young women. The common histopathological pattern was Class IV LN in 26 patients (44%). Three induction protocols were identified, along with systemic steroids: the high-dose cyclophosphamide protocol in 21 patients (35.6%), low-dose protocol in 4 patients (6.8%), and mycophenolate mofetil (MMF) in 41 patients (69.5%). Partial response, defined as the reduction of the 24-hour proteinuria by 25% at 3 months and 50% at 6 months, was achieved in 18 patients (33.3%) at 3 months and decreased to 13 patients (24.1%) at 6 months. Complete clinical response, defined as 24-hour urinary protein between 500 and 700 mg at 12 months, was achieved in 44 patients (81.5%). Complete remission was higher among patients with Class IV LN (64.4%). The achievement of partial clinical response at 3 months was significantly lower among patients with hypertension (P = .041). This study presented the LN remission rates in a single center in Saudi Arabia. Similar to previous studies, Class IV LN were the most common histopathological finding in this study. Complete remission at 12 months was achieved in 44 (81%) patients. Delayed remission is associated with hypertension at the time of LN diagnosis.

Extracellular mitochondrial components as new biomarkers for lupus nephritis.

Major reason for mortality among systemic lupus erythematosus patients is renal failure due to the deposition of immune complexes in the glomeruli. Being a chronic disease with multiple relapses and remissions across the lifespan, it's important to know the degree of nephritis for diagnosis as well as the long-term clinical management of the patients. Currently, renal biopsy is being used as the gold standard to diagnose and define the stages of the disease. However, renal biopsy being invasive only provides a localized picture of nephritis, and has the risk of bleeding. Additionally, it is also cost-intensive. Hence, a reliable, non-invasive biomarker is required for lupus nephritis. This study has evaluated extracellular mitochondrial components, including cell-free mitochondria, and cell-free mitochondrial DNA as probable biomarkers of the degree of nephritis. Both showed a significant correlation with proteinuria and protein-creatinine ratio. Our study substantiates their usage as clinical biomarkers of nephritis upon their validation in a larger cohort of lupus nephritis patients and other forms of nephritis. Although the current data suggest using cell-free mitochondria as a biomarker of lupus nephritis is better than the cell-free mitochondrial DNA.

Machine learning-based identification of novel hub genes associated with oxidative stress in lupus nephritis: implications for diagnosis and therapeutic targets.

BACKGROUND: Lupus nephritis (LN) is a complication of SLE characterised by immune dysfunction and oxidative stress (OS). Limited options exist for LN. We aimed to identify LN-related OS, highlighting the need for non-invasive diagnostic and therapeutic approaches. METHODS: LN-differentially expressed genes (DEGs) were extracted from Gene Expression Omnibus datasets (GSE32591, GSE112943 and GSE104948) and Molecular Signatures Database for OS-associated DEGs (OSEGs). Functional enrichment analysis was performed for OSEGs related to LN. Weighted gene co-expression network analysis identified hub genes related to OS-LN. These hub OSEGs were refined as biomarker candidates via least absolute shrinkage and selection operator. The predictive value was validated using receiver operating characteristic (ROC) curves and nomogram for LN prognosis. We evaluated LN immune cell infiltration using single-sample gene set enrichment analysis and CIBERSORT. Additionally, gene set enrichment analysis explored the functional enrichment of hub OSEGs in LN. RESULTS: The study identified four hub genes, namely STAT1, PRODH, TXN2 and SETX, associated with OS related to LN. These genes were validated for their diagnostic potential, and their involvement in LN pathogenesis was elucidated through ROC and nomogram. Additionally, alterations in immune cell composition in LN correlated with hub OSEG expression were observed. Immunohistochemical analysis reveals that the hub gene is most correlated with activated B cells and CD8 T cells. Finally, we uncovered that the enriched pathways of OSEGs were mainly involved in the PI3K-Akt pathway and the Janus kinase-signal transducer and activator of transcription pathway. CONCLUSION: These findings contribute to advancing our understanding of the complex interplay between OS, immune dysregulation and molecular pathways in LN, laying a foundation for the identification of potential diagnostic biomarkers and therapeutic targets.

Polygenic Risk Score Predicts Earlier-Onset Adult Systemic Lupus Erythematosus and First-Year Renal Diseases in a Taiwanese Cohort.

OBJECTIVES: This study aimed to develop a predictive model using polygenic risk score (PRS) to forecast renal outcomes for adult systemic lupus erythematosus (SLE) in a Taiwanese population. METHODS: Patients with SLE (n=2782) and matched non-SLE controls (n=11 128) were genotyped using Genome-Wide TWB 2.0 single-nucleotide polymorphism (SNP) array. PRS models (C+T, LDpred2, Lassosum, PRSice-2, PRS-continuous shrinkage (CS)) were constructed for predicting SLE susceptibility. Logistic regression was assessed for C+T-based PRS association with renal involvement in patients with SLE. RESULTS: In the training set, C+T-based SLE-PRS, only incorporating 27 SNPs, outperformed other models with area under the curve (AUC) values of 0.629, surpassing Lassosum (AUC=0.621), PRSice-2 (AUC=0.615), LDpred2 (AUC=0.609) and PRS-CS (AUC=0.602). Additionally, C+T-based SLE-PRS demonstrated consistent predictive capacity in the testing set (AUC=0.620). Individuals in the highest quartile exhibited earlier SLE onset (39.06 vs 44.22 years, p<0.01), higher Systemic Lupus Erythematosus Disease Activity Index scores (3.00 vs 2.37, p=0.04), elevated risks of renal involvement within the first year of SLE diagnosis, including WHO class III-IV lupus nephritis (OR 2.36, 95% CI 1.47 to 3.80, p<0.01), estimated glomerular filtration rate <60 mL/min/1.73m2 (OR 1.49, 95% CI 1.18 to 1.89, p<0.01) and urine protein-to-creatinine ratio >150 mg/day (OR 2.07, 95% CI 1.49 to 2.89, p<0.01), along with increased seropositivity risks, compared with those in the lowest quartile. Furthermore, among patients with SLE with onset before 50 years, the highest PRS quartile was significantly associated with more serious renal diseases within the first year of SLE diagnosis. CONCLUSIONS: PRS of SLE is associated with earlier onset, renal involvement within the first year of SLE diagnosis and seropositivity in Taiwanese patients. Integrating PRS with clinical decision-making may enhance lupus nephritis screening and early treatment to improve renal outcomes in patients with SLE.

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

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

Comparison of late-onset and non-late-onset systemic lupus erythematosus individuals in a real-world electronic health record cohort.

Objective: Late-onset systemic lupus erythematosus (LO-SLE) is defined as SLE diagnosed at age 50 years or later. Current studies on LO-SLE are small and have conflicting results.Methods: Using a large, electronic health record (EHR)-based cohort of SLE individuals, we compared demographics, disease characteristics, SLE-specific antibodies, and medication prescribing practices in LO (n = 123) vs. NLO-SLE (n = 402) individuals.Results: The median age (interquartile range) at SLE diagnosis was 60 (56-67) years for LO-SLE and 28 (20-38) years for NLO-SLE. Both groups were predominantly female (85% vs. 91%, p = 0.10). LO-SLE individuals were more likely to be White than NLO-SLE individuals (74% vs. 60%, p = 0.005) and less likely to have positive dsDNA (39% vs. 58%, p = 0.001) and RNP (17% vs. 32%, p = 0.02) with no differences in Smith, SSA, and SSB. Autoantibody positivity declined with increasing age at SLE diagnosis. LO-SLE individuals were less likely to develop SLE nephritis (9% vs. 29%, p < 0.001) and less likely to be prescribed multiple classes of SLE medications including antimalarials (90% vs. 95%, p = 0.04), azathioprine (17% vs. 31%, p = 0.002), mycophenolate mofetil (12% vs. 38%, p < 0.001), and belimumab (2% vs. 8%, p = 0.02).Conclusion: LO-SLE individuals may be less likely to fit an expected course for SLE with less frequent positive autoantibodies at diagnosis and lower rates of nephritis, even after adjusting for race. Understanding how age impacts SLE disease presentation could help reduce diagnostic delays in SLE.

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.

A critical view on autoantibodies in lupus nephritis: Concrete knowledge based on evidence.

Deposition of autoantibodies in glomeruli is a key factor in the development of lupus nephritis (LN). For a long time, anti-dsDNA and anti-C1q antibodies were thought to be the main cause of the kidney damage. However, recent studies have shown that the list of autoantibidies that have renal tropism and deposit in the kidney in LN is increasing and the link between anti-dsDNA and renal pathology is weak due to potential confounders. Aspecific bindings of dsDNA with cationic antibodies and of anti-dsDNA with several renal antigens such as actinin, laminin, entactin, and annexinA2 raised doubts about the specific target of these antibodies in the kidney. Moreover, the isotype of anti-dsDNA in SLE and LN has never received adequate interest until the recent observation that IgG2 are preponderant over IgG1, IgG3 and IgG4. Based on the above background, recent studies investigated the involvement of anti-dsDNA IgG2 and of other antibodies in LN. It was concluded that circulating anti-dsDNA IgG2 levels do not distinguish between LN versus non-renal SLE, and, in patients with LN, their levels do not change over time. Circulating levels of other antibodies such as anti-ENO1 and anti-H2 IgG2 were, instead, higher in LN vs non-renal SLE at the time of diagnosis and decreased following therapies. Finally, new classes of renal antibodies that potentially modify the anti-inflammatory response in the kidney are emerging as new co-actors in the pathogenetic scenario. They have been defined as 'second wave antibodies' for the link with detoxifying mechanisms limiting the oxidative stress in glomeruli that are classically stimulated in a second phase of inflammation. These findings have important clinical implications that may modify the laboratory approach to LN. Serum levels of anti-ENO1 and anti-H2 IgG2 should be measured in the follow up of patients for designing the length of therapies and identify those patients who respond to treatments. Anti-SOD2 could help to monitor and potentiate the anti-inflammatory response in the kidney.

Natural language processing to identify lupus nephritis phenotype in electronic health records.

BACKGROUND: Systemic lupus erythematosus (SLE) is a rare autoimmune disorder characterized by an unpredictable course of flares and remission with diverse manifestations. Lupus nephritis, one of the major disease manifestations of SLE for organ damage and mortality, is a key component of lupus classification criteria. Accurately identifying lupus nephritis in electronic health records (EHRs) would therefore benefit large cohort observational studies and clinical trials where characterization of the patient population is critical for recruitment, study design, and analysis. Lupus nephritis can be recognized through procedure codes and structured data, such as laboratory tests. However, other critical information documenting lupus nephritis, such as histologic reports from kidney biopsies and prior medical history narratives, require sophisticated text processing to mine information from pathology reports and clinical notes. In this study, we developed algorithms to identify lupus nephritis with and without natural language processing (NLP) using EHR data from the Northwestern Medicine Enterprise Data Warehouse (NMEDW). METHODS: We developed five algorithms: a rule-based algorithm using only structured data (baseline algorithm) and four algorithms using different NLP models. The first NLP model applied simple regular expression for keywords search combined with structured data. The other three NLP models were based on regularized logistic regression and used different sets of features including positive mention of concept unique identifiers (CUIs), number of appearances of CUIs, and a mixture of three components (i.e. a curated list of CUIs, regular expression concepts, structured data) respectively. The baseline algorithm and the best performing NLP algorithm were externally validated on a dataset from Vanderbilt University Medical Center (VUMC). RESULTS: Our best performing NLP model incorporated features from both structured data, regular expression concepts, and mapped concept unique identifiers (CUIs) and showed improved F measure in both the NMEDW (0.41 vs 0.79) and VUMC (0.52 vs 0.93) datasets compared to the baseline lupus nephritis algorithm. CONCLUSION: Our NLP MetaMap mixed model improved the F-measure greatly compared to the structured data only algorithm in both internal and external validation datasets. The NLP algorithms can serve as powerful tools to accurately identify lupus nephritis phenotype in EHR for clinical research and better targeted therapies.

Evaluating inter-rater reliability in the context of "Sysmex UN2000 detection of protein/creatinine ratio and of renal tubular epithelial cells can be used for screening lupus nephritis": a statistical examination.

BACKGROUND: The evaluation of inter-rater reliability (IRR) is integral to research designs involving the assessment of observational ratings by two raters. However, existing literature is often heterogeneous in reporting statistical procedures and the evaluation of IRR, although such information can impact subsequent hypothesis testing analyses. METHODS: This paper evaluates a recent publication by Chen et al., featured in BMC Nephrology, aiming to introduce an alternative statistical approach to assessing IRR and discuss its statistical properties. The study underscores the crucial need for selecting appropriate Kappa statistics, emphasizing the accurate computation, interpretation, and reporting of commonly used IRR statistics between two raters. RESULTS: The Cohen's Kappa statistic is typically used for two raters dealing with two categories or for unordered categorical variables having three or more categories. On the other hand, when assessing the concordance between two raters for ordered categorical variables with three or more categories, the commonly employed measure is the weighted Kappa. CONCLUSION: Chen and colleagues might have underestimated the agreement between AU5800 and UN2000. Although the statistical approach adopted in Chen et al.'s research did not alter their findings, it is important to underscore the importance of researchers being discerning in their choice of statistical techniques to address their specific research inquiries.

Prediction of treatment response in lupus nephritis using density of tubulointerstitial macrophage infiltration.

Background: Lupus nephritis (LN) is a common disease with diverse clinical and pathological manifestations. A major challenge in the management of LN is the inability to predict its treatment response at an early stage. The objective of this study was to determine whether the density of tubulointerstitial macrophage infiltration can be used to predict treatment response in LN and whether its addition to clinicopathological data at the time of biopsy would improve risk prediction. Methods: In this retrospective cohort study, 430 patients with LN in our hospital from January 2010 to December 2017 were included. We used immunohistochemistry to show macrophage and lymphocyte infiltration in their biopsy specimens, followed by quantification of the infiltration density. The outcome was the treatment response, defined as complete or partial remission at 12 months of immunosuppression. Results: The infiltration of CD68+ macrophages in the interstitium increased in patients with LN. High levels of CD68+ macrophage infiltration in the interstitium were associated with a low probability of treatment response in the adjusted analysis, and verse vice. The density of CD68+ macrophage infiltration in the interstitium alone predicted the response to immunosuppression (area under the curve [AUC], 0.70; 95% CI, 0.63 to 0.76). The addition of CD68+cells/interstitial field to the pathological and clinical data at biopsy in the prediction model resulted in an increased AUC of 0.78 (95% CI, 0.73 to 0.84). Conclusion: The density of tubulointerstitial macrophage infiltration is an independent predictor for treatment response in LN. Adding tubulointerstitial macrophage infiltration density to clinicopathological data at the time of biopsy significantly improves risk prediction of treatment response in LN patients.