Sandino-Bermúdez, Marlon J

Objective The aim of this study was to compare infection‐related hospitalization risk among patients with nonrenal systemic lupus erythematosus initiating commonly used immunosuppressants. Methods We emulated a target trial using Optum Labs Data Warehouse claims to compare the risk of infection‐related hospitalization among patients initiating azathioprine, belimumab, methotrexate, or mycophenolic acid analogues (MPAAs) between March 2011 and September 2023. We excluded patients with prior lupus nephritis, solid‐organ or bone marrow transplantation, or rituximab/cyclophosphamide exposure. The primary outcome was time to first infection‐related hospitalization using intention‐to‐treat (ITT) and per‐protocol (PP) analyses. We applied inverse probability of treatment weighting to account for baseline covariates and fitted marginal structural Cox models incorporating time‐varying monthly glucocorticoid dose during follow‐up. Results Among 6,168 patients, 24‐month cumulative incidence of infection‐related hospitalization was 10% (95% confidence interval [CI] 8–12) for azathioprine, 8% (95% CI 5–10) for belimumab, 10% (95% CI 8–11) for methotrexate, and 13% (95% CI 10–15) for MPAAs. In ITT analyses, MPAAs had higher risk than belimumab (hazard ratio [HR] 1.55, 95% CI 1.07–2.25) and methotrexate (HR 1.32, 95% CI 1.04–1.68). In PP analyses, azathioprine (HR 2.04, 95% CI 1.01–4.16) and MPAAs (HR 2.27, 95% CI 1.11–4.62) had higher risk compared with belimumab. After accounting for time‐varying monthly glucocorticoid dose, between‐treatment differences were no longer significant. Conclusion Initial differences in the infection‐related hospitalization risk were attenuated after accounting for time‐varying glucocorticoid exposure. These findings highlight glucocorticoid exposure as an important factor associated with serious infection risk while recognizing that postbaseline glucocorticoid use may reflect both evolving disease activity and a pathway through which therapies influence infection risk. image

Objective Antinuclear antibody (ANA) indirect immunofluorescence (IIF) is the reference standard but depends on subjective pattern interpretation. We tested whether artificial intelligence (AI) applied to ANA IIF images could identify specific autoantibodies. Methods We assembled a cohort of ANA‐positive patients (human epithelial type 2 IIF titer ≥1:80) with anti–double‐stranded DNA (dsDNA), anti‐Smith (Sm) antibody, ribonucleoprotein (RNP), anti‐Sjögren's disease‐related antigen A (SSA), anti‐Sjögren's disease‐related antigen B (SSB), anti‐topoisomerase I (Scl‐70), or centromere antibody (CMA) testing within 90 days. The development cohort (December 12, 2016–December 31, 2022) included the first ANA test per patient. Two AI architectures were trained for each autoantibody. Performance was assessed using area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and accuracy; comparisons with IIF patterns were summarized as pattern‐antibody agreement. A prospective cohort (January 1, 2023–August 20, 2024), including a dsDNA assay transition, provided temporal validation. Results Among 512,959 patients, 47,890 met inclusion criteria (mean age 55 [SD 17.6], 78% female). Models for CMA, dsDNA, Sm, SSA, and SSB achieved AUROC ≥0.80 (CMA highest: AUROC 0.95, accuracy 94.2%, specificity 95.3%). Compared with associated IIF patterns, dsDNA and Sm models more often classified antibody‐negative cases as negative (dsDNA 88.2% vs 54.7%; Sm 82.6% vs 60.3%) while similarly classifying antibody‐positive cases. Performance for RNP (AUROC 0.68) and Scl‐70 (AUROC 0.59) was lower. In the prospective cohort (n = 21,427), performance was similar; dsDNA discrimination remained stable across assays (AUROC ~0.85). Conclusion AI applied to ANA IIF images identified specific autoantibodies and often improved classification of antibody‐negative cases versus simplified pattern‐based comparators. These findings support its potential to standardize ANA interpretation and triage or reduce confirmatory testing. image