International Journal Of Rheumatic Diseases[JOURNAL]

INTRODUCTION: Systemic Lupus Erythematosus (SLE) presents a significant diagnostic challenge for clinicians due to its diverse clinical manifestations and overlap with other autoimmune conditions. Large Language Models (... INTRODUCTION: Systemic Lupus Erythematosus (SLE) presents a significant diagnostic challenge for clinicians due to its diverse clinical manifestations and overlap with other autoimmune conditions. Large Language Models (LLMs) are currently regarded as having the potential to assist clinicians in expediting decision-making. This study aimed to evaluate the performance of four LLMs in differentiating SLE from clinically mimicking conditions. METHODS: A retrospective diagnostic accuracy study was conducted involving 100 patients at a rheumatology center: 50 patients with confirmed SLE and 50 non-SLE patients with conditions including rheumatoid arthritis, systemic sclerosis, axial spondyloarthritis, psoriatic arthritis, myositis, ANCA-associated vasculitis, mixed connective tissue disease, undifferentiated connective tissue disease, and fibromyalgia. Four LLMs were evaluated: Deepseek, ChatGPT 4.0, Claude Sonnet 4, and Gemini. The 2019 European Alliance of Associations for Rheumatology/American College of Rheumatology (EULAR/ACR) classification criteria were applied. Diagnostic accuracy, positive predictive value (PPV), negative predictive value (NPV), and Area Under the Receiver Operating Characteristic Curve (AUC) were calculated. IBM SPSS Statistics version 25 was used for all analyses. RESULTS: Gemini achieved the highest performance score, with an accuracy of 96% (95% CI: 91.2-100.0%), sensitivity of 94% (95% CI: 89.3-98.7%), specificity of 98% (95% CI: 93.1-100.0%), and an AUC of 0.960. ChatGPT 4.0 and Claude Sonnet 4 exhibited comparable accuracy. Deepseek recorded the lowest performance score. CONCLUSION: Gemini demonstrated significant potential to assist clinicians in differentiating SLE from mimicking conditions. Nevertheless, prospective validation in real-world clinical settings is required before these tools can be reliably integrated into clinical practice.

Get PDF PubMed ↗

Distinct Clinical Phenotypes and Treatment Responses in IgG4-Related Disease: Insights From a Tertiary Care Centre in Western India.

Yadav S, Sachdev G, Balakrishnan C … +2 more , Samant R, Mangat G

Int J Rheum Dis · 2026 May · PMID 42178937 · Publisher ↗

BACKGROUND: IgG4-related disease (IgG4-RD) is a rare fibroinflammatory disorder characterized by tumefactive lesions and IgG4+ plasma cell infiltration. While corticosteroids induce remission, high relapse rates necessit... BACKGROUND: IgG4-related disease (IgG4-RD) is a rare fibroinflammatory disorder characterized by tumefactive lesions and IgG4+ plasma cell infiltration. While corticosteroids induce remission, high relapse rates necessitate steroid-sparing agents. Although well-studied in East Asia, comprehensive Indian data remain limited. METHODS: This retrospective study (2018-2024) analyzed 60 biopsy-evaluated patients diagnosed per the 2020 Revised Comprehensive Diagnostic Criteria. All received glucocorticoid induction; steroid-sparing agents were initiated concurrently in 97%. Treatment response was assessed using the IgG4-RD Responder Index (complete response [CR]: RI < 3 with ≥ 2-point reduction; partial response [PR]: ≥ 2-point reduction with RI ≥ 3; relapse: ≥ 2-point rise after response). RESULTS: The cohort (n = 60) was 57% male, mean age of 46.4 ± 16.1 years. Most had definite IgG4-RD (63%), and 42% presented with multisystem involvement. Distinct from East Asian cohorts, retroperitoneal fibrosis (32%) and lung involvement (28%) predominated, with pancreatic (5% vs. 60% in Japan) and salivary gland disease (25% vs. 72%) were rare. Histopathology revealed universal lymphoplasmacytic infiltrates (100%) and fibrosis (93%), but infrequent storiform fibrosis (7%) and obliterative phlebitis (12%). Treatment yielded a 90% response rate at 6 months (28% CR, 62% PR), improving to 52% CR at 2 years. Despite excellent induction, cumulative relapse reached 66% at a median of 13 months follow-up, underscoring the disease's chronic nature. In a small subgroup receiving rituximab plus methotrexate (n = 4), 75% achieved CR with no documented relapses at 2 years; larger studies are needed to confirm this signal. One death occurred from urosepsis. CONCLUSION: Indian IgG4-RD patients exhibit younger onset, retroperitoneal-lung predominance, and minimal pancreatic involvement. Early combination immunosuppression provides excellent initial responses but cannot prevent the disease's relapsing nature, underscoring the need for long-term maintenance strategies and region-specific management approaches.

Get PDF PubMed ↗

Real-World Safety and Retention of Tofacitinib in Elderly Versus Non-elderly Patients With Rheumatoid Arthritis: A Retrospective Cohort Study in Taiwan.

Chiang LH, Tsai PH, Chen YF … +3 more , Yu CL, Tsai TC, Fang YF

Int J Rheum Dis · 2026 May · PMID 42177625 · Publisher ↗

OBJECTIVES: Tofacitinib, the first approved oral small-molecule Janus kinase inhibitor (JAKi), is widely used for treating rheumatoid arthritis (RA). This study aims to compare the drug retention rates of tofacitinib bet... OBJECTIVES: Tofacitinib, the first approved oral small-molecule Janus kinase inhibitor (JAKi), is widely used for treating rheumatoid arthritis (RA). This study aims to compare the drug retention rates of tofacitinib between elderly (≥ 65 years) and nonelderly (< 65 years) RA patients in a real-world clinical setting in Taiwan and to identify clinical factors associated with treatment discontinuation. METHODS: We conducted a retrospective cohort study of RA patients receiving tofacitinib between 2015 and 2020, with follow-up until December 31, 2021. Patients were categorized into an elderly group (≥ 65 years, n = 82) and a nonelderly group (< 65 years, n = 224). Drug discontinuation was defined as the cessation of tofacitinib during follow-up. Primary outcomes included retention rates, reasons for discontinuation, and the incidence of adverse events. Kaplan-Meier analysis and multivariate Cox proportional hazards models were used to identify independent factors for discontinuation. RESULTS: A total of 306 RA patients were included (mean age: 56.97 ± 12.44 years). The elderly group had a significantly higher prevalence of comorbidities, including hypertension, diabetes, hyperlipidemia, and osteoporosis. There was no significant difference in mean treatment duration (2.70 ± 1.73 vs. 2.61 ± 1.69 years, p = 0.7049). Kaplan-Meier analysis showed no statistically significant difference in retention rates (Log-rank test, p = 0.425). Multivariate analysis revealed that age was not an independent risk factor for discontinuation (adjusted HR = 1.086, 95% CI: 0.729-1.618, p = 0.685). Among 40 patients who discontinued due to adverse events, serious infection was the leading cause (35.0%), comprising 10 non-fatal serious infection events and 4 infection-related deaths. Major adverse cardiovascular events (MACE) occurred only in the elderly group (15.8%). CONCLUSIONS: In real-world practice, the drug retention of tofacitinib in elderly RA patients is comparable to that in nonelderly patients. Despite a higher comorbidity burden, age itself is not an independent risk factor for treatment discontinuation. However, the risk of MACE is higher in elderly patients, necessitating careful cardiovascular assessment and monitoring before tofacitinib treatment. These findings suggest that tofacitinib is a viable option for elderly RA patients, provided individualized risk assessment is performed. Notably, discontinuation due to adverse events was substantially less frequent than discontinuation due to lack of efficacy, supporting the overall favorable tolerability of tofacitinib in this population.

Get PDF PubMed ↗