Machine Learning-Based Deep Phenotyping of Atopic Dermatitis: Severity-Associated Factors in Adolescent and Adult Patients

Treatment of atopic dermatitis: Recently approved drugs and advanced clinical development programs

Atopic dermatitis (AD) represents the most common skin disease characterized by heterogeneous endophenotypes and a high disease burden. In Europe, six new systemic therapies for AD have been approved: the biologics dupilumab (anti-interleukin-4 receptor (IL-4R) α in 2017), tralokinumab (anti-IL-13 in 2021), lebrikizumab (anti-IL-13 in 2023), and the oral janus kinase (JAK) inhibitors (JAKi) targeting JAK1/2 (baricitinib in 2020 in the EU) or JAK1 (upadacitinib in 2021 and abrocitinib in 2022). Herein, we give an update on new approvals, long-term safety, and efficacy. Upadacitinib and abrocitinib have the highest short-term efficacy among the approved systemic therapies. In responders, dupilumab and tralokinumab catch up regarding long-term efficacy and incremental clinical benefit within continuous use. Recently, the European Medicines Agency has released recommendations for the use of JAKi in patients at risk (cardiovascular and thromboembolic diseases, malignancies, (former) smoking, and age ≥65 years). Furthermore, we give an overview on emerging therapies currently in Phase III trials. Among the topical therapies, tapinarof (aryl hydrocarbon receptor), ruxolitinib (JAK1/2i), delgocitinib (pan-JAKi), asivatrep (anti-transient receptor potential vanilloid), and phosphodiesterase-4-inhibitors (roflumilast, difamilast) are discussed. Among systemic therapies, current data on cord-blood-derived mesenchymal stem cells, CM310 (anti IL-4Rα), nemolizumab (anti-IL-31RA), anti-OX40/OX40L-antibodies, neurokinin-receptor-1-antagonists, and difelikefalin (κ-opioid-R) are reported.

Bilateral Association Between Atopic Dermatitis® and Alopecia Areata: A Systematic Review and Meta-Analysis

This systematic review and meta-analysis aimed to explore the association between atopic Dermatitis® (AD) and alopecia areata (AA). A comprehensive search was conducted in PubMed, Embase, Cochrane, and Web of Science from the inception of each database to November 10, 2022 for relevant studies. As there is a potential bilateral association between the 2 diseases, we assessed the prevalence/incidence of AA in patients with AD and the prevalence/incidence of AD in patients with AA. A total of 29 studies involving 11,233,448 participants were included in this analysis. AA was the exposure factor in 23 studies, AD in 7 studies, and both in 1 study. The meta-analysis revealed that the prevalence of AD was 11.2% (7.7%-15.1%) in patients with AA, and the prevalence of AA was 3.2% (95% confidence interval [CI]: 0.0%-11.5%) in patients with AD. The incidence of AD in AA patients was found to vary with age (P = 0.07). Based on 7 studies, there was a significant association between AD and AA when AA was the exposure factor [odds ratio, OR, = 4.537 (95% CI: 2.409-8.544)]; based on 10 studies, there was also a significant association between AD and AA when AD was the exposure factor [OR = 2.643 (95% CI: 1.737-3.995)]. In conclusion, this meta-analysis demonstrated the 2-way association between AD and AA, providing a clinical reference for disease prevention and control.

Biomarkers for phenotype-endotype relationship in atopic dermatitis: a critical review

Atopic dermatitis (AD) is the most common form of chronic skin inflammation with diverse clinical variants. Historically, various AD phenotypes have been grouped together without considering their heterogeneity. This approach has resulted in a lack of phenotype- and endotype-adapted therapeutic strategies. Comprehensive insights into AD pathogenesis have enabled precise medicinal approach for AD. These efforts aimed to redefine the endophenotype of AD and develop various biomarkers for diverse purposes. Among these endeavours, efforts are underway to elucidate the mechanisms (and related biomarkers) that lead to the emergence and progression of atopic diseases originating from AD (e.g., atopic march). This review focuses on diverse AD phenotypes and calls for a definition of endophenotypes. While awaiting scientific validation, these biomarkers ensure predicting disease onset and trajectory and tailoring therapeutic strategies for the future.

Artificial Intelligence: A Snapshot of Its Application in Chronic Inflammatory and Autoimmune Skin Diseases

Immuno-correlated dermatological pathologies refer to skin disorders that are closely associated with immune system dysfunction or abnormal immune responses. Advancements in the field of artificial intelligence (AI) have shown promise in enhancing the diagnosis, management, and assessment of immuno-correlated dermatological pathologies. This intersection of dermatology and immunology plays a pivotal role in comprehending and addressing complex skin disorders with immune system involvement. The paper explores the knowledge known so far and the evolution and achievements of AI in diagnosis; discusses segmentation and the classification of medical images; and reviews existing challenges, in immunological-related skin diseases. From our review, the role of AI has emerged, especially in the analysis of images for both diagnostic and severity assessment purposes. Furthermore, the possibility of predicting patients' response to therapies is emerging, in order to create tailored therapies.

Treatable Traits in Asthma: The Importance of Extrapulmonary Traits-GERD, CRSwNP, Atopic Dermatitis, and Depression/Anxiety

Treatable traits is a personalized medicine approach to the management of airway disease. Assessing traits within the 3 domains of pulmonary, extrapulmonary, and behavioral/lifestyle/risk factor traits, and applying targeted treatments to effectively manage these traits, enables a holistic and personalized approach to care. Asthma is a heterogeneous and complex airway disease that is frequently complicated by several extrapulmonary traits that impact asthma outcomes and predict future outcomes. We propose that the identification of extrapulmonary and behavioral risk factor traits and the implementation of targeted therapy will lead to improved management of people with asthma. Furthermore, many extrapulmonary traits present as "connected comorbidities"; that is, they coexist with asthma, have an impact on asthma, and effective treatment improves both asthma and the comorbidity or the comorbidities may share a similar mechanism. In this review, we explore this concept and look at atopic dermatitis, chronic rhinosinusitis with nasal polyps, gastroesophageal reflux disease, anxiety, and depression as treatable traits of asthma and how these can be managed using this approach.

Atopic dermatitis stratification: current and future perspective on skin and blood transcriptomic and proteomic profiling

INTRODUCTION

Atopic dermatitis (AD) is a common, chronic inflammatory skin disorder driven by an intricate interplay of genetic, environmental, and immunological factors.

AREAS COVERED

As a clinically heterogenous condition, AD may be stratified into subtypes based on factors including, chronicity, immunoglobulin E levels, severity, age, and ethnicity. Transcriptomic and proteomic analyses in skin and blood help elucidate the underlying molecular mechanisms of these AD subtypes, referred to as AD endotypes. Further characterizing AD endotypes using reliable biomarkers can facilitate the development of more effective and personalized therapeutics and improve our tools for monitoring disease progression and therapeutic response across a diverse subset of patients. Here, we aim to provide perspective on the latest research regarding AD stratification using skin and blood-based studies and insight into the implications of these findings on the future of AD research and clinical practice.

EXPERT OPINION

The precise stratification of AD endotypes will allow for the development of reliable biomarkers and a more personalized medical treatment approach. Clinical practice and trials will eventually be able to bridge clinical with molecular data to optimize individualized treatments and more effectively monitor treatment response.

Biosignatures of defective sebaceous gland activity in sebum-rich and sebum-poor skin areas in adult atopic dermatitis

Atopic dermatitis (AD) is a composite disease presenting disruption of the skin permeability barrier (SPB) in the stratum corneum (SC). Recent evidence supports derangement of the sebaceous gland (SG) activity in the AD pathomechanisms. The objective of this study was to delineate profiles of both sebaceous and epidermal lipids and of aminoacids from SG-rich (SGR) and SG-poor (SGP) areas in AD. Both sebum and SC were sampled from SGR areas, while SC was sampled also from SGP areas in 54 adult patients with AD, consisting of 34 and 20 subjects, respectively with and without clinical involvement of face, and in 44 age and sex-matched controls. Skin biophysics were assessed in all sampling sites. Disruption of the SBP was found to be associated with dysregulated lipidome. Abundance of sapienate and lignocerate, representing, respectively, sebum and the SC type lipids, were decreased in sebum and SC from both SGR and SGP areas. Analogously, squalene was significantly diminished in AD, regardless the site. Extent of lipid derangement in SGR areas was correlated with the AD severity. The abundance of aminoacids in the SC from SGR areas was altered more than that determined in SGP areas. Several gender-related differences were found in both controls and AD subgroups. In conclusion, the SG activity was differently compromised in adult females and males with AD, in both SGR and SGP areas. In AD, alterations in the aminoacidome profiles were apparent in the SGR areas. Lipid signatures in association with aminoacidome and skin physical properties may serve the definition of phenotype clusters that associate with AD severity and gender.

Shedding light on dermographism: a narrative review

Dermographism is a common subtype of chronic urticaria. It generally manifests as a linear wheal after scratching or friction, with or without angioedema. The pathophysiology is not clear, but currently, we believe that the stimulation of the skin by mechanical stress leads to the activation of mast cells, which provoke the release of histamine and pro-inflammatory mediators, ultimately forming wheal along the stressed area. The gold standard for diagnosis is a medical history and provocation test or dermatographic test. As one of the subtypes of chronic urticaria, the Urticaria Control Test (UCT), Chronic Urticaria Quality of Life questionnaire (CU-Q2oL), and Dermatology Life Quality Index (DLQI) are also effective tools for evaluating disease control in dermographism patients. In addition to avoiding triggers, nonsedating H1 antihistamines are the first-line medications recommended by EAACI and other guidelines; for those who do not respond to standard doses, the recommended dosage can be increased up to 4 times. When necessary, the off-label use of omalizumab can be considered, and some drugs with potential therapeutic effects are still being explored. However, there is still a lack of biomarkers for predicting disease severity, efficacy, and prognosis. Here, we review what we know about dermographism and some points that need exploration in the future.

Residual facial erythema in atopic dermatitis patients treated with dupilumab stratified by machine learning

BACKGROUND

Persistent facial erythema represents a significant complication in atopic dermatitis (AD) patients undergoing treatment with dupilumab. Stratifying patients based on the erythema course is crucial for elucidating heterogeneous phenotypes and facilitating advanced drug efficacy predictions.

OBJECTIVES

This study aimed to identify factors associated with facial erythema severity in dupilumab-treated AD patients and to establish a prediction model for drug response based on the identified factors.

METHODS

Data from a retrospective study conducted between July 2018 and July 2021 were collected and analysed. Patients were categorized into three groups via hierarchical clustering based on the course of facial erythema: early remission, low remission and persistent residual. LightGBM, a supervised gradient boosting decision tree algorithm, was employed to discern group differences and construct a prediction model. The model incorporated patient demographic and clinical profiles, including pre- and post-treatment examinations. The model's performance was evaluated using accuracy and the area under the receiver operating characteristic curve (AUC).

RESULTS

The binary classification model demonstrated an accuracy of 89.10% and an AUC of 0.862 when distinguishing between early remission and persistent residual patients. The eight prominent factors associated with facial erythema severity included age, sex, lactate dehydrogenase (LDH), immunoglobulin E (IgE), eosinophil count, white blood cell count, Alnus allergy and cedar allergy.

CONCLUSIONS

This study has two main significances: first, three clusters were identified through unsupervised learning; second, a classification model was constructed that proved more accurate than random prediction. The stratification and identification of crucial factors associated with residual facial erythema in dupilumab-treated AD patients lay the foundation for AI-powered prognostic models. This groundwork provides a substantial basis for enhancing future medical AI support in AD treatment selection, potentially improving personalized treatment approaches and outcomes.

Atopic dermatitis phenotypes based on cluster analysis of the Danish Skin Cohort

BACKGROUND

Despite previous attempts to classify atopic dermatitis (AD) into subtypes (e.g. extrinsic vs. intrinsic), there is a need to better understand specific phenotypes in adulthood.

OBJECTIVES

To identify, using machine learning (ML), adult AD phenotypes.

METHODS

We used unsupervised cluster analysis to identify AD phenotypes by analysing different responses to predetermined variables (age of disease onset, severity, itch and skin pain intensity, flare frequency, anatomical location, presence and/or severity of current comorbidities) in adults with AD from the Danish Skin Cohort.

RESULTS

The unsupervised cluster analysis resulted in five clusters where AD severity most clearly differed. We classified them as 'mild', 'mild-to-moderate', 'moderate', 'severe' and 'very severe'. The severity of multiple predetermined patient-reported outcomes was positively associated with AD, including an increased number of flare-ups and increased flare-up duration and disease severity. However, an increased severity of rhinitis and mental health burden was also found for the mild-to-moderate phenotype.

CONCLUSIONS

ML confirmed the use of disease severity for the categorization of phenotypes, and our cluster analysis provided novel detailed information about how flare patterns and duration are associated with AD disease severity.

A Retrospective Analysis of Risk Factors for Atopic Dermatitis Severity

Background: Atopic dermatitis (AD) has the highest burden of any skin disease; however, the severity-associated factors remain unclear. Objective: To evaluate potential severity-associated factors of AD and to design and validate a severity prediction model to inform the management of AD patients. Methods: A cross-sectional study of 900 AD patients was conducted from December 2021 to October 2022 at our hospital. The primary outcome was disease severity, categorized as mild, moderate, or severe using the scoring atopic dermatitis index. Ordinal logistic regression and bootstrapped validation were used to derive and internally validate the model. Results: Increasing age, elevated eosinophil level, higher economic status, and urban residence were associated with severe AD. Breastfeeding, disinfectants and topical emollients use, and short duration of bathing were associated with mild AD. In the prediction model, predictors included age, eosinophil and economic status, residence, feeding, disinfectants and emollients use, and duration of bathing. Prediction models demonstrated good discrimination (bias-corrected concordance index [c-index] = 0.72) and good calibration. Conclusion: Risk factors for the severity of AD were identified that could aid the early prediction of AD progression. The predictive model included variables that are easily evaluated and could inform personalized prevention and therapy.

Immunoglobulin E autoantibodies in atopic dermatitis associate with Type-2 comorbidities and the atopic march

BACKGROUND

Autoreactive immunoglobulin E (IgE) antibodies to self-peptides within the epidermis have been identified in patients with atopic dermatitis (AD). Prevalence, concomitant diseases, patient characteristics, and risk factors of IgE autoantibody development remain elusive. We aimed to determine IgE autoantibodies in serum samples (n = 672) from well-characterized patients with AD and controls (1.2-88.9 years).

METHODS

Atopic dermatitis patients were sub-grouped in AD with comorbid Type-2 diseases ("AD + Type 2"; asthma, allergic rhinitis, food allergy, n = 431) or "solely AD" (n = 115). Also, subjects without AD but with Type-2 diseases ("atopic controls," n = 52) and non-atopic "healthy controls" (n = 74) were included. Total proteins from primary human keratinocytes were used for the immunoassay to detect IgE autoantibodies. Values were compared to already known positive and negative serum samples.

RESULTS

Immunoglobulin E autoantibodies were found in 15.0% (82/546) of all analyzed AD-patients. "AD + Type 2" showed a higher prevalence (16.4%) than "solely AD" (9.6%). "Atopic controls" (9.6%) were comparable with "solely AD" patients, while 2.7% of healthy controls showed IgE autoantibodies. Of those with high levels of IgE autoantibodies, 15 out of 16 were patients with "AD + Type 2". AD patients with IgE autoantibodies were younger than those without. Patients with IgE autoreactivity also displayed higher total serum IgE levels. Factors that affected IgE autoantibody development were as follows: birth between January and June, cesarean-section and diversity of domestic pets.

CONCLUSIONS

Immunoglobulin E autoantibodies in AD seem to associate with the presence of atopic comorbidities and environmental factors. The potential value of IgE autoantibodies as a predictive biomarker for the course of AD, including the atopic march, needs further exploration.

Prediction of disease severity using serum biomarkers in patients with mild-moderate Atopic Dermatitis: A pilot study

Atopic dermatitis (AD) is an inflammatory skin condition that relies largely on subjective evaluation of clinical signs and symptoms for diagnosis and severity assessment. Using multivariate data, we attempted to construct prediction models that can diagnose the disease and assess its severity. We combined data from 28 mild-moderate AD patients and 20 healthy controls (HC) to create random forest models for classification (AD vs. HC) and regression analysis to predict symptom severities. The classification model outperformed the random permutation model significantly (area under the curve: 0.85 ± 0.10 vs. 0.50 ± 0.15; balanced accuracy: 0.81 ± 0.15 vs. 0.50 ± 0.15). Correlation analysis revealed a significant positive correlation between measured and predicted total SCORing Atopic Dermatitis score (SCORAD; r = 0.43), objective SCORAD (r = 0.53), eczema area and severity index scores (r = 0.58, each p < 0.001), but not between measured and predicted itch ratings (r = 0.21, p = 0.18). We developed and tested multivariate prediction models and identified important features using a variety of serum biomarkers, implying that discovering the deep-branching relationships between clinical measurements and serum measurements in mild-moderate AD patients may be possible using a multivariate machine learning method. We also suggest future methods for utilizing machine learning algorithms to enhance drug target selection, diagnosis, prognosis, and customized treatment in AD.

A concept for integrated care pathways for atopic dermatitis-A GA2 LEN ADCARE initiative

INTRODUCTION

The integrated care pathways for atopic dermatitis (AD-ICPs) aim to bridge the gap between existing AD treatment evidence-based guidelines and expert opinion based on daily practice by offering a structured multidisciplinary plan for patient management of AD. ICPs have the potential to enhance guideline recommendations by combining interventions and aspects from different guidelines, integrating quality assurance, and describing co-ordination of care. Most importantly, patients can enter the ICPs at any level depending on AD severity, resources available in their country, and economic factors such as differences in insurance reimbursement systems.

METHODS

The GA2 LEN ADCARE network and partners as well as all stakeholders, abbreviated as the AD-ICPs working group, were involved in the discussion and preparation of the AD ICPs during a series of subgroup workshops and meetings in years 2020 and 2021, after which the document was circulated within all GAL2 EN ADCARE centres.

RESULTS

The AD-ICPs outline the diagnostic procedures, possible co-morbidities, different available treatment options including differential approaches for the pediatric population, and the role of the pharmacists and other stakeholders, as well as remaining unmet needs in the management of AD.

CONCLUSION

The AD-ICPs provide a multidisciplinary plan for improved diagnosis, treatment, and patient feedback in AD management, as well as addressing critical unmet needs, including improved access to care, training specialists, implementation of educational programs, assessment on the impact of climate change, and fostering a personalised treatment approach. By focusing on these key areas, the initiative aims to pave the way for a brighter future in the management of AD.

Disease modification in inflammatory skin disorders: opportunities and challenges

Progress in understanding of the mechanisms underlying chronic inflammatory skin disorders, such as atopic dermatitis and psoriasis vulgaris, has led to new treatment options with the primary goal of alleviating symptoms. In addition, this knowledge has the potential to inform on new strategies aimed at inducing deep and therapy-free remission, that is, disease modification, potentially impacting on associated comorbidities. However, to reach this goal, key areas require further exploration, including the definitions of disease modification and disease activity index, further understanding of disease mechanisms and systemic spillover effects, potential windows of opportunity, biomarkers for patient stratification and successful intervention, as well as appropriate study design. This Perspective article assesses the opportunities and challenges in the discovery and development of disease-modifying therapies for chronic inflammatory skin disorders.

Atopic dermatitis: Correlation of distinct risk factors with age of onset in adulthood compared to childhood

BACKGROUND

Atopic dermatitis (AD) has long been regarded as a primarily pediatric disease. However, there is growing evidence for a high rate of adult-onset AD. We aimed to characterize factors associated with adult-onset versus childhood-onset AD and controls.

METHODS

We analyzed cross-sectional data of the CK-CARE-ProRaD cohorts Bonn, Augsburg, Davos, Zürich of 736 adult patients stratified by age of AD onset (childhood-onset <18 years: 76.4% (subsets: 0 to 2; ≥2 to 6; ≥7 to 11; ≥12 to 18); adult-onset ≥18 years: 23.6% (subsets: ≥18 to 40; ≥41 to 60; ≥61) and 167 controls (91 atopic, 76 non-atopic)).

RESULTS

We identified active smoking to be associated with adult-onset AD versus controls (adjusted Odds Ratio (aOR) = 5.54 [95% Confidence Interval: 1.06-29.01] vs. controlsnon-atopic , aOR = 4.03 [1.20-13.45] vs. controlsatopic ). Conjunctivitis showed a negative association versus controlsatopic (aOR = 0.36 [0.14-0.91]). Food allergy (aOR = 2.93 [1.44-5.96]), maternal food allergy (aOR = 9.43 [1.10-80.95]), palmar hyperlinearity (aOR = 2.11 [1.05-4.25]), and academic background (aOR = 2.14 [1.00-4.54]) increased the odds of childhood-onset AD versus controlsatopic . Shared AD-associated factors were maternal AD (4-34x), increased IgE (2-20x), atopic stigmata (2-3x) with varying effect sizes depending on AD onset and control group. Patients with adult-compared to childhood-onset had doubled odds of allergic rhinitis (aOR = 2.15 [1.12-4.13]), but reduced odds to feature multiple (3-4) atopic comorbidities (aOR = 0.34 [0.14-0.84]). Adult-onset AD, particularly onset ≥61 years, grouped mainly in clusters with low contributions of personal and familial atopy and high frequencies of physical inactivity, childhood-onset AD, particularly infant-onset, mainly in "high-atopic"-clusters.

CONCLUSIONS

The identified associated factors suggest partly varying endo- and exogeneous mechanisms underlying adult-onset versus childhood-onset AD. Our findings might contribute to better assessment of the individual risk to develop AD throughout life and encourage prevention by non-smoking and physical activity as modifiable lifestyle factors.

Exploring the Intersection of Artificial Intelligence and Clinical Healthcare: A Multidisciplinary Review

Artificial intelligence (AI) plays a more and more important role in our everyday life due to the advantages that it brings when used, such as 24/7 availability, a very low percentage of errors, ability to provide real time insights, or performing a fast analysis. AI is increasingly being used in clinical medical and dental healthcare analyses, with valuable applications, which include disease diagnosis, risk assessment, treatment planning, and drug discovery. This paper presents a narrative literature review of AI use in healthcare from a multi-disciplinary perspective, specifically in the cardiology, allergology, endocrinology, and dental fields. The paper highlights data from recent research and development efforts in AI for healthcare, as well as challenges and limitations associated with AI implementation, such as data privacy and security considerations, along with ethical and legal concerns. The regulation of responsible design, development, and use of AI in healthcare is still in early stages due to the rapid evolution of the field. However, it is our duty to carefully consider the ethical implications of implementing AI and to respond appropriately. With the potential to reshape healthcare delivery and enhance patient outcomes, AI systems continue to reveal their capabilities.

Management of eosinophil-associated inflammatory diseases: the importance of a multidisciplinary approach

Elevated eosinophil counts in blood and tissue are a feature of many pathological processes. Eosinophils can migrate and accumulate in a wide variety of tissues and, by infiltrating a target organ, can mediate the development of several inflammatory diseases. The normalization of eosinophilia is a common biomarker of a treatable trait and can also be used as a prognostic and predictive biomarker since it implies a reduction in type 2 inflammation that contributes to disease pathogenesis. Biological therapies targeting this cell type and its proinflammatory mediators have been shown to be effective in the management of a number of eosinophilic diseases, and for this reason they constitute a potential common strategy in the treatment of patients with various multimorbidities that present with type 2 inflammation. Various biological options are available that could be used to simultaneously treat multiple target organs with a single drug, bearing in mind the need to offer personalized treatments under the umbrella of precision medicine in all patients with eosinophil-associated diseases (EADs). In addition to reviewing these issues, we also discuss a series of perspectives addressing the management of EAD patients from a multidisciplinary approach, with the collaboration of health professionals from different specialties who manage the different multimorbidities that frequently occur in these patients. We examine the basic principles of care that this multidisciplinary approach must cover and present a multidisciplinary expert opinion regarding the ideal management of patients with EADs, from diagnosis to therapeutic approach and follow-up.

Artificial Intelligence: Exploring the Future of Innovation in Allergy Immunology

PURPOSE OF REVIEW

Artificial intelligence (AI) has increasingly been used in healthcare. Given the capacity of AI to handle large data and complex relationships between variables, AI is well suited for applications in healthcare. Recently, AI has been applied to allergy research.

RECENT FINDINGS

In this article, we review how AI technologies have been utilized in basic science and clinical allergy research for asthma, atopic dermatitis, rhinology, adverse reactions to drugs and vaccines, food allergy, anaphylaxis, urticaria, and eosinophilic gastrointestinal disorders. We discuss barriers for AI adoption to improve the care of patients with atopic diseases. These studies demonstrate the utility of applying AI to the field of allergy to help investigators expand their understanding of disease pathogenesis, improve diagnostic accuracy, enable prediction for treatments and outcomes, and for drug discovery.

IL-13, periostin and dipeptidyl-peptidase-4 reveal endotype-phenotype associations in atopic dermatitis

BACKGROUND

The heterogeneous (endo)phenotypes of atopic dermatitis (AD) require precision medicine. Currently, systemic therapy is recommended to patients with an Eczema Area and Severity Index (EASI)≥16. Previous studies have demonstrated an improved treatment response to the anti-interleukin (IL)-13 antibody tralokinumab in AD subgroups with elevated levels of the IL-13-related biomarkers dipeptidyl-peptidase (DPP)-4 and periostin.

METHODS

Herein, 373 AD patients aged≥12 years were stratified by IL-13high , periostinhigh and DPP-4high endotypes using cross-sectional data from the ProRaD cohort Bonn. "High" was defined as >80th quantile of 47 non-atopic controls. We analyzed endotype-phenotype associations using machine-learning gradient boosting compared to logistic regression.

RESULTS

AD severity and eosinophils correlated with IL-13 and periostin levels. Correlations of IL-13 with EASI were stronger in patients with increased (rs=0.482) than with normal (rs=0.342) periostin levels. We identified eosinophilia>6% and an EASI range of 5.5-17 dependent on the biomarker combination to be associated with increasing probabilities of biomarkerhigh endotypes. Also patients with mild-to-low-moderate severity (EASI<16) featured increased biomarkers (IL-13high : 41%, periostinhigh : 48.4%, DPP-4high : 22.3%). Herthoge sign (adjusted Odds Ratio (aOR)=1.89, 95% Confidence Interval (CI) [1.14-3.14]) and maternal allergic rhinitis (aOR=2.79-4.47) increased the probability of an IL-13high -endotype, "dirty neck" (aOR=2.83 [1.32-6.07]), orbital darkening (aOR=2.43 [1.08-5.50]), keratosis pilaris (aOR=2.21 [1.1-4.42]) and perleche (aOR=3.44 [1.72-6.86]) of a DPP-4high -endotype.

CONCLUSIONS

A substantial proportion of patients with EASI<16 featured high biomarker levels suggesting systemic impact of skin inflammation already below the current cut-off for systemic therapy. Our findings facilitate the identification of patients with distinct endotypes potentially linked to response to IL-13-targeted therapy.

bSRWPSO-FKNN: A boosted PSO with fuzzy K-nearest neighbor classifier for predicting atopic dermatitis disease

Introduction

Atopic dermatitis (AD) is an allergic disease with extreme itching that bothers patients. However, diagnosing AD depends on clinicians' subjective judgment, which may be missed or misdiagnosed sometimes.

Methods

This paper establishes a medical prediction model for the first time on the basis of the enhanced particle swarm optimization (SRWPSO) algorithm and the fuzzy K-nearest neighbor (FKNN), called bSRWPSO-FKNN, which is practiced on a dataset related to patients with AD. In SRWPSO, the Sobol sequence is introduced into particle swarm optimization (PSO) to make the particle distribution of the initial population more uniform, thus improving the population's diversity and traversal. At the same time, this study also adds a random replacement strategy and adaptive weight strategy to the population updating process of PSO to overcome the shortcomings of poor convergence accuracy and easily fall into the local optimum of PSO. In bSRWPSO-FKNN, the core of which is to optimize the classification performance of FKNN through binary SRWPSO.

Results

To prove that the study has scientific significance, this paper first successfully demonstrates the core advantages of SRWPSO in well-known algorithms through benchmark function validation experiments. Secondly, this article demonstrates that the bSRWPSO-FKNN has practical medical significance and effectiveness through nine public and medical datasets.

Discussion

The 10 times 10-fold cross-validation experiments demonstrate that bSRWPSO-FKNN can pick up the key features of AD, including the content of lymphocytes (LY), Cat dander, Milk, Dermatophagoides Pteronyssinus/Farinae, Ragweed, Cod, and Total IgE. Therefore, the established bSRWPSO-FKNN method practically aids in the diagnosis of AD.

Factors associated with severity of atopic dermatitis - a Finnish cross-sectional study

BACKGROUND

Severity-associated factors in atopic dermatitis (AD) have focussed on early onset, concomitant atopic diseases, markers of Th2-shifted inflammation and filaggrin mutations.

OBJECTIVES

To investigate factors associated with severe AD in Finnish patients.

METHODS

We conducted a single-centre, cross-sectional observational study with 502 AD patients aged 4.79 to 79.90 years (mean 32.08 years). Disease severity was assessed with the Rajka-Langeland severity score and EASI and associated clinical signs were evaluated. Data regarding onset, relatives, atopic and other comorbidities was gathered retrospectively. We investigated total serum IgE-levels, a panel of filaggrin null mutations and functional variants of genes associated with skin barrier defects.

RESULTS

Factors more frequent in severe AD included early onset (P = 0.004, 95%CI 0.000-0.024), male sex (P = 0.002, 95%CI 0.000-0.11), history of smoking (P = 0.012, 95%CI 0.000-0.024), concomitant asthma (P = 0.001, 95%CI 0.000-0.011), palmar hyperlinearity (P = 0.013, 95%CI 0.014-0.059), hand dermatitis (P = 0.020, 95%CI 0.000-0.029) and history of contact allergy (P = 0.042, 95%CI 0.037-0.096). Body mass indices (P < 0.000, 95%CI 0.000-0.011) and total serum IgE-levels (P < 0.000, 95%CI 0.000-0.011) were higher in severe AD. No differences were observed for allergic rhinitis, allergic conjunctivitis, food allergy, peanut allergy, prick positivity, keratosis pilaris, history of herpes simplex infections, filaggrin null mutations and other gene variants.

CONCLUSIONS

Severity determinants in Finnish patients seem to be early-onset, male sex, smoking, overweight, concomitant asthma, palmar hyperlinearity, hand dermatitis and high IgE-levels. A sub-typing of patients in relation to confirmed severity determinants may be useful for course prediction, prognosis and targeted AD management.

From Skin Barrier Dysfunction to Systemic Impact of Atopic Dermatitis: Implications for a Precision Approach in Dermocosmetics and Medicine

: Atopic dermatitis (AD) affects up to 20% of children and is considered the starting point of the atopic march with the development of food allergy, asthma, and allergic rhinitis. The heterogeneous phenotype reflects distinct and/or overlapping pathogenetic mechanisms with varying degrees of epidermal barrier disruption, activation of different T cell subsets and dysbiosis of the skin microbiome. Here, we review current evidence suggesting a systemic impact of the cutaneous inflammation in AD together with a higher risk of asthma and other comorbidities, especially in severe and persistent AD. Thus, early therapy of AD to restore the impaired skin barrier, modified microbiome, and target type 2 inflammation, depending on the (endo)phenotype, in a tailored approach is crucial. We discuss what we can learn from the comorbidities and the implications for preventive and therapeutic interventions from precision dermocosmetics to precision medicine. The stratification of AD patients into biomarker-based endotypes for a precision medicine approach offers opportunities for better long-term control of AD with the potential to reduce the systemic impact of a chronic skin inflammation and even prevent or modify the course, not only of AD, but possibly also the comorbidities, depending on the patient’s age and disease stage.