Objective Comparison of oral corticosteroid (OCS) use in patients with SLE in a US rheumatology network pre- and post-belimumab initiation. Methods This retrospective cohort study (GSK Study 214140) used data from the Patient-Important Outcomes Data Repository (PIONEER)-Rheumatology database. Eligible adults with SLE initiated belimumab between 1 January 2012 and 30 June 2021, and had available data for >180 days pre- and >360 days post-belimumab initiation. The index was the date of belimumab initiation. Changes in OCS use were measured by: proportion of patients receiving OCS; mean total OCS dose/patient; mean total number of OCS days supplied/patient; mean daily OCS dose for days supplied/patient; the proportion of patients with OCS doses of ≤5 mg/day and ≤7.5 mg/day for days supplied. These changes were assessed between period (P)1 (6 months pre-index) and P2 (first 6 months post-index) and P3 (second 6 months post-index) in patients with OCS use in P1 who persisted with belimumab at each assessed period. Results Overall, 608 patients received belimumab for 180 days (full analysis set (FAS)) and 492 for 360 days. Most patients were female (92.8%); 70.4% had moderate SLE. In P1, 56.3% of FAS patients and 54.5% of patients who persisted with belimumab for 360 days received OCS. Among patients receiving OCS in P1, significantly fewer patients received OCS in P2 (78.4%) and P3 (64.9%) vs P1 (100.0%). Significant reductions from P1 were observed in P2 and P3 in the mean total OCS dose/patient, the mean OCS daily dose for days supplied and the proportions of patients with OCS dose of ≤5 mg/day and ≤7.5 mg/day, and the mean total OCS days supplied/patient in P3 only. Conclusions This analysis showed significant reductions in OCS dose and use in patients with SLE who persisted with belimumab, providing more real-world evidence for belimumab’s steroid-sparing effect.

Systemic lupus erythematosus (SLE) is a complex autoimmune disease that poses serious long-term patient burdens. (1) Background: SLE patient classification and care are often complicated by case heterogeneity (diverse variations in symptoms and severity). Large language models (LLMs) and generative artificial intelligence (genAI) may mitigate this challenge by profiling medical records to assess key medical criteria. (2) Methods: To demonstrate genAI-based profiling, ACR (American College of Rheumatology) 1997 SLE classification criteria were used to define medically relevant LLM prompts. Records from 78 previously studied patients (45 classified as having SLE; 33 indeterminate or negative) were computationally profiled, via five genAI replicate runs. (3) Results: GenAI determinations of the “Discoid Rash” and “Pleuritis or Pericarditis” classification criteria yielded perfect concurrence with clinical classification, while some factors such as “Immunologic Disorder” (56% accuracy) were statistically unreliable. Compared to clinical classification, our genAI approach achieved a 72% predictive success rate. (4) Conclusions: GenAI classifications may prove sufficiently predictive to aid medical professionals in evaluating SLE patients and structuring care strategies. For individual criteria, accuracy seems to correlate inversely with complexities in clinical determination, implying that improvements in AI patient profiling tools may emerge from continued advances in clinical classification efficacy.

Introduction Patients with systemic lupus erythematosus (SLE) have variable treatment pathways, including antimalarials, glucocorticoids, immunosuppressants, and/or biologics. This study describes differences in clinical outcomes when initiating belimumab (BEL) before and after immunosuppressant use. Methods This real-world, retrospective cohort study (GSK Study 217536) used de-identified administrative claims data from January 2015 to December 2022 in the Komodo Health Database. Adults with moderate/severe SLE initiating BEL (index date) were identified from January 2017 to May 2022, allowing a ≥ 24-month baseline period. Patients were stratified into those initiating BEL before immunosuppressant use (no immunosuppressant use within 24 months before index) and those initiating BEL after immunosuppressant use (one immunosuppressant used within 24 months before index). Oral glucocorticoid (OGC) use, SLE flares, new organ damage, and all-cause healthcare resource utilization (HCRU) were analyzed descriptively over a 24-month follow-up. Results Baseline SLE severity was similar for patients initiating BEL before (n = 2295) versus after (n = 4114) immunosuppressant use (moderate, 83.1% vs 79.0%; severe, 16.8% vs 21.0%). Patients initiating BEL before versus after immunosuppressant use had lower SLE flare rates and OGC use. Post-index, patients initiating BEL before versus after immunosuppressant use discontinued their OGC sooner (moderate baseline SLE, 4.5 vs 8.9 months; severe baseline SLE, 6.2 vs 11.6 months). Patients initiating BEL before versus after immunosuppressant use had lower SLE flare rates per person-year at all time points (especially severe flare rates in patients with severe baseline SLE, 0.70 vs 1.48 through 24 months post-index). Median time to new organ damage occurrence was longer in patients initiating BEL before versus after immunosuppressant use (moderate baseline SLE, 32.1 vs 26.7 months; severe baseline SLE, 22.7 vs 21.6 months). All-cause HCRU was similar between cohorts. Conclusions These results suggest that patients initiating BEL before versus after immunosuppressant use had more favorable outcomes.

Case. A 50-year-old African American male presented with abdominal pain and significant weight loss. On physical examination, he had parotid and submandibular gland enlargement associated with right eye proptosis. Computed tomography showed a thoracic paravertebral soft tissue mass, enlarged lymph nodes, and ascending aortic aneurysm. Laboratory results were remarkable for elevated total IgG and IgG4 subclass. The submandibular gland pathology revealed chronic sclerosing sialadenitis, with a large subset of inflammatory cells positively staining for IgG4. The histology of the paravertebral mass demonstrated fibrosclerosis with increased lymphocytic infiltrate, associated with increased IgG4 plasma cells. He was diagnosed with immunoglobulin G4-related disease (IgG4-RD). Steroid therapy initially yielded improvement; however, after steroids were stopped, there was disease recurrence. Prednisone was restarted, and the plan was to start him on rituximab. Interestingly, the patient’s brother also had IgG4-RD. Conclusion. IgG4-RD can present as a paravertebral mass which is usually responsive to steroids; however, recurrent and resistant disease can be seen for which steroid-sparing agents such as rituximab should be considered. In addition, to the best of our knowledge, this is the first reported case of IgG4-RD in two family members presenting as a paravertebral mass, highlighting an exciting area for more research in the future.

Introduction This study examined the benefit of belimumab as standard treatment in patients with systemic lupus erythematosus (SLE) treated without versus with immunosuppressants (IS) prior to belimumab initiation. Methods This retrospective cohort study (GSK Study 217537) used healthcare claims from the US Komodo Health Database from January 2015 to October 2023. Eligible adults had ≥ 1 inpatient or ≥ 2 outpatient SLE diagnosis codes, ≥ 1 belimumab claim (January 2017–October 2023; index date) and 24 months continuous data pre-index. Two cohorts were defined: those with ≥ 1 claim for non-IS SLE treatment (antimalarials, oral glucocorticoids [OGC] or biologics; non-IS cohort) or ≥ 1 claim for incident IS (IS cohort) within 12 months pre-index. Cohort comparability was assessed across the 12 months before non-IS/IS treatment, applying inverse probability of treatment weighting (IPTW) to adjust for confounding. Outcomes included OGC use, SLE flare rates and healthcare resource utilisation, compared using Cox, Poisson regression and logit models, respectively. Results Overall, 2190 and 2533 patients were included in IPTW-adjusted non-IS and IS cohorts, respectively. The non-IS cohort had a median (95% confidence interval [CI]) time to OGC discontinuation of 9.8 (8.2, 12.2) months versus 11.7 (10.5, 13.4) for the IS cohort, and a 30% higher likelihood of OGC discontinuation (hazard ratio [95% CI] 1.30 [1.11, 1.52]). The likelihood of OGC dose reduction and discontinuation or dose reduction alone was similar between cohorts. The non-IS versus IS cohort had a lower incidence rate ratio (IRR [95% CI]) of total (0.94 [0.92, 0.96]) and moderate (0.77 [0.74, 0.80]) SLE flares, with similar odds of SLE-related inpatient stays (odds ratio [95% CI] 1.12 [0.94, 1.34]) and emergency visits (1.02 [0.82, 1.27]). Conclusion In this large, retrospective, real-word study using IPTW adjustment, initiating belimumab without prior IS use was associated with OGC-sparing benefits and reduced incidence and severity of SLE flares.

Background/Objectives: In clinical informatics, the term ‘information overload’ is increasingly used to describe the operational impediments of excessive documentation. While electronic health records (EHRs) are growing in abundance, many medical records (MRs) remain in legacy formats that impede efficient, systematic processing, contributing to the extenuating challenges of care fragmentation. Thus, there is a growing interest in using generative AI (genAI) for automated MR summarization and characterization. Methods: MRs for a set of 78 individuals were digitized. Some were known systemic lupus erythematosus (SLE) cases, while others were under evaluation for possible SLE classification. A two-pass genAI assessment strategy was implemented using the Claude 3.5 large language model (LLM) to mine MRs for information relevant to classifying SLE vs. undifferentiated connective tissue disorder (UCTD) vs. neither via the 22-criteria EULAR 2019 model. Results: Compared to clinical determination, the antinuclear antibody (ANA) criterion (whose results are crucial for classifying SLE-negative cases) exhibited favorable sensitivity 0.78 ± 0.09 (95% confidence interval) and a positive predictive value 0.85 ± 0.08 but a marginal performance for specificity 0.60 ± 0.11 and uncertain predictivity for the negative predictive value 0.48 ± 0.11. Averaged over the remaining 21 criteria, these four performance metrics were 0.69 ± 0.11, 0.87 ± 0.04, 0.54 ± 0.10, and 0.93 ± 0.03. Conclusions: ANA performance statistics imply that genAI yields confident assessments of SLE negativity (per high sensitivity) but weaker positivity. The remaining genAI criterial determinations support (per specificity) confident assertions of SLE-positivity but tend to misclassify a significant fraction of clinical positives as UCTD.