天疱瘡

BACKGROUND: Rituximab (RTX) combined with glucocorticoids (GCs) is a first-line treatment for pemphigus, yet short-term prognostic outcomes and their predictors remain underexplored in Chinese populations. OBJECTIVE: To evaluate the 52-week outcomes of RTX combined with GCs in a real-world Chinese cohort and identify independent predictors of complete remission on minimal therapy (CR mini) and relapse. METHODS: This multicenter retrospective study included 276 pemphigus patients who received initial RTX combined with GCs. Univariate and multivariate logistic regression analyses were performed to identify predictors of CR mini and relapse. RESULTS: Over 52 weeks, 134 (48.6%) patients achieved CR mini, and 35 (12.7%) relapsed. Independent predictors for CR mini were three RTX infusions, higher baseline IgM level and absence of baseline herpes simplex virus infection. For relapse, independent predictors were higher body weight, prior immunosuppressant use, and prior cyclophosphamide use. Adverse events occurred in 23.2% of patients, primarily infections, with no significant differences across prognostic subgroups. LIMITATIONS: Retrospective design and absence of dynamic biomarkers. CONCLUSION: This study identifies readily obtainable baseline predictors for CR mini and relapse in RTX-treated pemphigus, facilitating early risk stratification and individualized treatment strategies to optimize long-term outcomes.

OBJECTIVE: We aimed to characterize the inflammatory and complication profiles of patients with retroperitoneal unicentric Castleman disease (UCD), compare the clinical features of UCD with an MCD-like inflammatory state (UCD-MIS) and non-MIS cases, and describe treatment patterns and follow-up outcomes. MATERIALS AND METHODS: We retrospectively analyzed 75 patients with retroperitoneal UCD treated at our institution between 2000 and 2025, focusing on inflammatory phenotypes, severe complications, surgical extent, and follow-up outcomes. RESULTS: UCD-MIS was identified in 20 patients (26.7%). Paraneoplastic pemphigus (PNP) occurred in 9 patients (12.0%), bronchiolitis obliterans (BO) in 8 (10.7%), and amyloid A (AA) amyloidosis in 2 (2.7%). Patients with UCD-MIS more frequently had PNP (35.0% vs. 3.6%; FDR-adjusted P = 0.004) and BO (25.0% vs. 5.5%; FDR-adjusted P = 0.042) than those without MIS. For treatment, 61 patients underwent surgery, including 57 complete resections. During a median follow-up of 60.8 months (range, 6.1-266.2 months), two deaths occurred. Both patients had PNP and met the criteria for UCD-MIS, and one also had BO. Neither patient had undergone surgical excision of the UCD lesion. The small number of deaths precluded between-group survival comparisons. CONCLUSION: Comprehensive screening for complications is essential in retroperitoneal UCD, and complete surgical excision remains the cornerstone of therapy when technically feasible.

Background/Objectives: To compare the diagnostic performance of Claude Opus 4.7 and Gemini Pro 3 for the differential diagnosis of oral autoimmune blistering diseases (AIBDs) and evaluate their diagnostic reasoning, confidence, and calibration. Materials and Methods: This retrospective multicenter paired diagnostic accuracy study included 200 clinicopathologically confirmed AIBD cases (50 each of pemphigus vulgaris, mucous membrane pemphigoid, bullous pemphigoid, and linear IgA bullous dermatosis). Each case was independently assessed by both models using identical standardized clinical information and clinical photographic inputs. The task required forced-choice classification among the four predefined diseases. Histopathological and direct immunofluorescence findings were used exclusively to establish the clinicopathological reference diagnosis and were not provided to the AI models. The reference diagnosis was established by clinicopathological correlation. The primary outcome was diagnostic accuracy. Secondary outcomes included disease-specific diagnostic performance, Cohen's κ, ROC analysis, calibration, confidence, reasoning quality, management recommendations, and error patterns. Pre-consensus inter-rater reliability of the two human assessors was also evaluated using Cohen's κ for binary outcomes and weighted Cohen's κ for the ordinal reasoning-quality score. Results: Claude achieved significantly higher diagnostic accuracy than Gemini (92.0% vs. 86.0%, p = 0.012), stronger agreement with the reference standard (κ = 0.893 vs. 0.813), and superior discrimination (macro-AUC 0.998 vs. 0.965). Claude demonstrated higher key diagnostic-feature identification (92.0% vs. 86.0%; p = 0.012) and higher clinical-reasoning scores (61.0% vs. 40.0% of responses rated good; Wilcoxon p < 0.001; r = 0.47), whereas management recommendations did not differ significantly (100.0% vs. 98.0%; p = 0.125). Calibration results were metric-dependent: Claude had a lower one-vs-rest Brier score (0.0468 vs. 0.0558), whereas Gemini had a lower expected calibration error (0.083 vs. 0.251). For both models, the predominant error was misclassification of linear IgA bullous dermatosis as mucous membrane pemphigoid. Conclusions: Both multimodal LLMs showed high performance in this controlled four-class benchmark, with Claude Opus 4.7 outperforming Gemini Pro 3 in overall accuracy and reasoning quality. However, these findings do not establish autonomous diagnostic capability, clinical effectiveness, or safety. The LABD-MMP misclassification and metric-dependent calibration highlight important limitations. The models should therefore be regarded as investigational adjunctive decision-support tools requiring clinician oversight and diagnostic verification. Prospective external and human-in-the-loop validation is required before clinical implementation.