Identification of chronic urticaria subtypes using machine learning algorithms

Autoimmune Diseases and Low Baseline IgE in Chronic Spontaneous Urticaria: A Clinical and Therapeutic Prospective Analysis in Real-Life Clinical Practice

BACKGROUND

Autoimmunity contributes to the pathogenesis of chronic spontaneous urticaria (CSU). The subtyping of CSU has revealed an autoimmune form of CSU. Despite autoimmune diseases having been associated with CSU, there are few prospective studies that have evaluated the characteristics and biomarkers of patients with CSU and autoimmune disease in a real-life practice setting.

OBJECTIVE

To evaluate the presence of specific biomarkers for the presence of autoimmune disease in CSU and to analyze the clinical and therapeutic features of patients with CSU and autoimmune disease.

METHODS

The clinical, laboratory, and therapeutic features of patients with CSU at a tertiary-level center were prospectively collected. Data obtained were compared in function of the presence/absence of autoimmune disease and typified according to IgE levels.

RESULTS

Patients with CSU who had associated autoimmune disease corresponded to middle-aged women with a common pattern of blood test findings: both low baseline IgE and high-affinity receptor of IgE expression, basopenia, eosinopenia, higher baseline erythrocyte sedimentation rate and D-dimer, increased presence of antinuclear antibodies, IgG against thyroid peroxidase, and positive autologous serum skin test result. Total baseline IgE less than or equal to 43.8 IU/mL was both the optimal cutoff to predict autoimmune disease in the CSU cohort and a significant risk factor for the presence of autoimmune disease in the regression analysis.

CONCLUSIONS

In real-life clinical practice, characteristics of patients with CSU and autoimmune disease share common features with type IIb autoimmune CSU. Total baseline IgE less than or equal to 43.8 IU/mL has been detected as a possible biomarker of autoimmune disease in patients with CSU.

Recent updates in urticaria

Urticaria is a skin-condition characterized by sudden-onset pruritic wheals with/without angioedema. Urticaria can be acute or chronic. Chronic urticaria may be spontaneous or inducible, based on absence/presence of specific triggers. Chronic spontaneous urticaria is most frequent (∼80%). Urticaria is primarily a mast-cell mediated histaminergic-disorder. Recently, other inflammatory cells and pro-inflammatory cytokines have been implicated. Deeper understanding has unmasked two endotypes - IgE-mediated type I autoimmunity/autoallergy and IgG-mediated type IIb autoimmunity. Current treatment recommendation involving second-generation H1-antihistamines, omalizumab and cyclosporine is effective in 60-80% patients. So, newer treatment options are being explored based on emerging targets. Despite being non-lethal, urticaria considerably impairs patient's quality-of-life and may be associated with extra-cutaneous comorbidities. Several "patient reported outcome measures" have been proposed to evaluate disease-activity, impact and control, for effective treatment modulation till complete disease control. This review discusses the current understanding about urticaria and its future directions, to facilitate optimum evidenced-based care.

Artificial intelligence-driven drug development against autoimmune diseases

Artificial intelligence (AI)-based predictive models are being used to foster a precision medicine approach to treat complex chronic diseases such as autoimmune and autoinflammatory disorders (AIIDs). In the past few years the first models of systemic lupus erythematosus (SLE), primary Sjögren syndrome (pSS), and rheumatoid arthritis (RA) have been produced by molecular profiling of patients using omic technologies and integrating the data with AI. These advances have confirmed a complex pathophysiology involving multiple proinflammatory pathways and also provide evidence for shared molecular dysregulation across different AIIDs. I discuss how models are used to stratify patients, assess causality in pathophysiology, design drug candidates in silico, and predict drug efficacy in virtual patients. By relating individual patient characteristics to the predicted properties of millions of drug candidates, these models can improve the management of AIIDs through more personalized treatments.

EAACI guidelines on environmental science in allergic diseases and asthma - Leveraging artificial intelligence and machine learning to develop a causality model in exposomics

Allergic diseases and asthma are intrinsically linked to the environment we live in and to patterns of exposure. The integrated approach to understanding the effects of exposures on the immune system includes the ongoing collection of large-scale and complex data. This requires sophisticated methods to take full advantage of what this data can offer. Here we discuss the progress and further promise of applying artificial intelligence and machine-learning approaches to help unlock the power of complex environmental data sets toward providing causality models of exposure and intervention. We discuss a range of relevant machine-learning paradigms and models including the way such models are trained and validated together with examples of machine learning applied to allergic disease in the context of specific environmental exposures as well as attempts to tie these environmental data streams to the full representative exposome. We also discuss the promise of artificial intelligence in personalized medicine and the methodological approaches to healthcare with the final AI to improve public health.

Autoimmune chronic spontaneous urticaria

Chronic spontaneous urticaria (CSU) is a debilitating mast cell-driven disease characterized by recurrent wheals and/or angioedema. Substantial progress has been made in dissecting the 2 main autoimmune mechanisms that drive the pathogenesis of CSU. Type I autoimmune (autoallergic) CSU is associated with IgE antibodies against autoantigens, for example, thyroid peroxidase and IL-24. Type IIb autoimmune CSU is mediated by autoantibodies that activate mast cells, for example, via IgE and FcεRI, and is present in less than 10% of patients with CSU when strict criteria are used, that is, triple positivity of autologous serum skin test, immunoassays for IgG autoantibodies, and basophil activation tests. A subpopulation of patients with CSU has both types. Type IIb autoimmune CSU is characterized by higher disease severity, concomitant autoimmune diseases, low levels of total IgE, elevated levels of IgG-anti-thyroid peroxidase, basopenia, eosinopenia, poor response to antihistamines and to omalizumab, and a good response to cyclosporine. Novel targeted therapies for CSU are under development such as ligelizumab, an anti-IgE, fenebrutinib and remibrutinib, Bruton's tyrosine kinase inhibitors, and dupilumab, an anti-IL-4Rα. Further studies should investigate the overlap between autoallergic and type IIb autoimmune CSU, optimize the diagnosis of both autoimmune endotypes using easy-to-perform, noninvasive, and inexpensive markers, and assess differences in response to therapy.