Clinical Overlapping in Autoinflammatory Diseases: The Role of Gene Duplication

Accuracy of generative artificial intelligence models in differential diagnoses of familial Mediterranean fever and deficiency of Interleukin-1 receptor antagonist

With the increasing development of artificial intelligence, large language models (LLMs) have been utilized to solve problems in natural language processing tasks. More recently, LLMs have shown unique potential in numerous applications within medicine but have been particularly investigated for their ability in clinical reasoning. Although the diagnostic accuracy of LLMs in forming differential diagnoses has been reviewed in general internal medicine applications, much is unknown in autoinflammatory disorders. From the nature of autoinflammatory diseases, forming a differential diagnosis is challenging due to the overlapping symptoms between disorders and even more difficult without genetic screening. In this work, the diagnostic accuracy of the Generative Pre-Trained Transformer Model-4 (GPT-4), GPT-3.5, and Large Language Model Meta AI (LLaMa) were evaluated in clinical vignettes of Deficiency of Interleukin-1 Receptor Antagonist (DIRA) and Familial Mediterranean Fever (FMF). We then compared these models to a control group including one internal medicine physician. It was found that GPT-4 did not significantly differ in correctly identifying DIRA and FMF patients compared to the internist. However, the physician maintained a significantly higher accuracy than GPT-3.5 and LLaMa 2 for either disease. Overall, we explore and discuss the unique potential of LLMs in diagnostics for autoimmune diseases.

A Pro-Inflammatory Signature Constitutively Activated in Monogenic Autoinflammatory Diseases

Autoinflammatory diseases (AIDs) are disorders characterised by recurrent inflammatory episodes in charge of different organs with no apparent involvement of autoantibodies or antigen-specific T lymphocytes. Few common clinical features have been identified among all monogenic AIDs (mAIDs), while the search for a common molecular pattern is still ongoing. The aim of this study was to increase knowledge on the inflammatory pathways in the development of mAIDs in order to identify possible predictive or diagnostic biomarkers for each disease and to develop future preventive and therapeutic strategies. Using protein array-based systems, we evaluated two signalling pathways known to be involved in inflammation and a wide range of inflammatory mediators (pro-inflammatory cytokines and chemokines) in a cohort of 23 patients affected by different mAIDs, as FMF, TRAPS, MKD, Blau syndrome (BS), and NLRP12D. Overall, we observed upregulation of multiple signalling pathway intermediates at protein levels in mAIDs patients’ PBMCs, compared with healthy controls, with significant differences also between patients. FMF, TRAPS, and BS presented also peculiar activations of inflammatory pathways that can distinguish them. MAPK pathway activation, however, seems to be a common feature. The serum level of cytokines and chemokines produced clear differences between patients with distinct diseases, which can help distinguish each autoinflammatory disease. The FMF cytokine production profile appears broader than that of TRAPS, which, in turn, has higher cytokine levels than BS. Our findings suggest an ongoing subclinical inflammation related to the abnormal and constitutive signalling pathways and define an elevated inflammatory cytokine signature. Moreover, the upregulation of Th17-related cytokines emphasises the important role for Th17 and/or Th17-like cells also in monogenic AIDs.

Prenatal detection and molecular cytogenetic characterization of 19q13.42 microduplication: three reported cases and literature review

Background

Trisomy 19q is a recognizable syndrome and associated with a wide spectrum of clinical phenotypes in clinic. The purpose of this study was to explore the prenatal phenotypes of 19q13.42 duplication, which was rarely reported in clinic.

Case presentation

Three pregnant women presenting diverse indications for prenatal diagnosis accepted amniocentesis: increased nuchal translucency and fetal pyelic separation (case 2) and high risk of maternal serum screening for Down syndrome (case 1 and case 3). Case 1 and case 2 shared similar duplicated locus in the region of 19q13.42, encompassing part NLRP12 gene. The latter inherited the chromosomal duplication from the mother with normal phenotypes. Case 3 carried a 1.445 Mb duplication in the 19q13.42q13.43 region. It was proposed that evolutionary duplication of NLRP12 gene could have a causative role in autoinflammatory diseases development. The genotype–phenotype correlation depends mainly on the duplicated size and functional genes involved, which is still yet to be determined. All pregnant women chose to continue the pregnancy and delivered healthy children with no apparent abnormalities.

Conclusions

The 19q13.42 microduplications in our study were the smallest fragments compared to previous literature. Our findings enriched the prenatal phenotypes for this chromosomal microscopic imbalance. It was proposed that long term follow up analysis should be guaranteed till adulthood to determine whether there will be other emerging clinical symptoms and developmental-behavioral disorders for such carriers.