Modeling Wheezing Spells Identifies Phenotypes with Different Outcomes and Genetic Associates

Epidemiology of asthma across the ages

In the past 3 decades, the overall prevalence of asthma appears to be plateauing, although large geographic and socioeconomic variation is evident. Overall, asthma prevalence slightly decreased in most age groups, except for school-aged children. Of note, asthma mortality steadily decreased, potentially highlighting improved asthma management strategies. Several epidemiologic studies indicate that a complex interplay between genetic, environmental, and immunologic factors predisposes individuals to asthma inception and persistence across different life stages. Established risk factors for preschool wheezing to asthma persistence comprise a combination of pre- and post-natal parameters including the maternal history of asthma, prematurity, caesarian section, early-life respiratory infections, exposure to air pollution or tobacco smoke, and allergic polysensitization. On the other hand, persistence into adulthood is mainly driven by disease severity, allergic multimorbidity, relevant comorbidities, severe respiratory infections, and tobacco smoke exposure. It is evident that asthma prevention strategies do not fit a "one size fits all" concept and key environmental interventions should be tailored to different regions of the world. Undoubtedly, the heterogeneity of asthma as a disease is at least partly reflected in the reported epidemiologic measures, and continuing, methodologically rigorous studies will allow us to unravel some of the observed discrepancies.

Tracing the path from preschool wheezing to asthma

This short review illustrates, using two recent studies, the potential and challenges of using machine learning methods to identify phenotypes of wheezing and asthma from childhood onwards.

Molecular allergy diagnosis enabling personalized medicine

Allergic patients are characterized by complex and patient-specific IgE sensitization profiles to various allergens, which are accompanied by different phenotypes of allergic disease. Molecular allergy diagnosis establishes the patient's IgE reactivity profile at a molecular allergen level and has moved allergology into the era of precision medicine. Molecular allergology started in the late 1980s with the isolation of the first allergen-encoding DNA sequences. Already in 2002, the first allergen microarrays were developed for the assessment of complex IgE sensitization patterns. Recombinant allergens are used for a precise definition of personal IgE reactivity profiles, identification of genuine IgE sensitization to allergen sources for refined prescription of allergen-specific immunotherapy and allergen avoidance diagnosis of co- versus cross-sensitization, epidemiologic studies, and prediction of symptoms, phenotypes, and development of allergic disease. For example, molecular IgE sensitization patterns associated with more severe respiratory allergies, severe food allergy, and allergy to honeybee or vespids are already established. The implementation of molecular allergy diagnosis into daily clinical practice requires continuous medical education and training doctors in molecular allergy diagnosis, and may be facilitated by clinical decision support systems such as diagnostic algorithms that may take advantage of artificial intelligence.

Artificial intelligence in pediatric allergy research

Atopic dermatitis, food allergy, allergic rhinitis, and asthma are among the most common diseases in childhood. They are heterogeneous diseases, can co-exist in their development, and manifest complex associations with other disorders and environmental and hereditary factors. Elucidating these intricacies by identifying clinically distinguishable groups and actionable risk factors will allow for better understanding of the diseases, which will enhance clinical management and benefit society and affected individuals and families. Artificial intelligence (AI) is a promising tool in this context, enabling discovery of meaningful patterns in complex data. Numerous studies within pediatric allergy have and continue to use AI, primarily to characterize disease endotypes/phenotypes and to develop models to predict future disease outcomes. However, most implementations have used relatively simplistic data from one source, such as questionnaires. In addition, methodological approaches and reporting are lacking. This review provides a practical hands-on guide for conducting AI-based studies in pediatric allergy, including (1) an introduction to essential AI concepts and techniques, (2) a blueprint for structuring analysis pipelines (from selection of variables to interpretation of results), and (3) an overview of common pitfalls and remedies. Furthermore, the state-of-the art in the implementation of AI in pediatric allergy research, as well as implications and future perspectives are discussed.

CONCLUSION

AI-based solutions will undoubtedly transform pediatric allergy research, as showcased by promising findings and innovative technical solutions, but to fully harness the potential, methodologically robust implementation of more advanced techniques on richer data will be needed.

WHAT IS KNOWN

• Pediatric allergies are heterogeneous and common, inflicting substantial morbidity and societal costs. • The field of artificial intelligence is undergoing rapid development, with increasing implementation in various fields of medicine and research.

WHAT IS NEW

• Promising applications of AI in pediatric allergy have been reported, but implementation largely lags behind other fields, particularly in regard to use of advanced algorithms and non-tabular data. Furthermore, lacking reporting on computational approaches hampers evidence synthesis and critical appraisal. • Multi-center collaborations with multi-omics and rich unstructured data as well as utilization of deep learning algorithms are lacking and will likely provide the most impactful discoveries.

Preschool wheeze and asthma endotypes- implications for future therapy

INTRODUCTION

Preschool wheeze and school-aged asthma present a large healthcare burden. Both conditions are now recognized to be heterogeneous, with similar symptom presentation but likely different underlying lung pathology.

AREAS COVERED

Current treatment options for preschool wheeze are constrained by extrapolations from the management of school-aged children with asthma. While most cases of asthma at school age are caused by classical atopic, eosinophilic, Type-2 driven asthma, only a quarter of preschool children with wheeze fall into this category. Targeting treatment to specific underlying mechanisms resulting in preschool wheeze may alter the progression to school age asthma. Novel biologics have revolutionized the management of severe, treatment-resistant school age asthma, but a limited evidence base limits their use in young children. There are several potential future non-steroid-based treatment options in development, of which bacterial lysates show the most promise.

EXPERT OPINION

Effective treatment of preschool wheeze may preserve lung function into later life, which may alter the progression trajectory toward school age asthma. Endotype-driven management will enable more effective treatment of both preschool wheeze and school age asthma.

Association of urinary eosinophilic protein X at age 3 years and subsequent persistence of wheezing and asthma diagnosis in adolescence

BACKGROUND

Wheezing is common in early life, but most children stop wheezing by school age. However, the prediction of course of wheezing through childhood is difficult.

OBJECTIVE

To investigate whether urinary EPX (a marker of eosinophil activation) in children at age 3 years may be useful for the prediction of wheeze persistence and future asthma diagnosis.

METHODS

U-EPX was measured at age 3 years (radioimmunoassay) in 906 participants in the population-based birth cohort. Children attended follow-ups to age 16 years. We investigate the discriminative ability of u-EPX and other factors in predicting asthma diagnosis at age 16 using receiver operating characteristic [ROC] curves.

RESULTS

Of 613 children with follow-up information at age 16, 511 had data on u-EPX at age 3 and asthma diagnosis at age 16 years; of those; 133 (21.7%) had asthma. Based on longitudinal data, children were assigned to wheeze clusters: No wheeze (NWZ), early transient (ETW), late-onset (LOW), intermittent (INT) and persistent wheeze (PEW). U-EPX levels differed significantly between different wheeze clusters (p = .003), with clusters characterised with persistent symptoms having higher u-EPX. In the whole cohort, the best performing classification model for asthma diagnosis at age 16 years included sex, u-EPX, sensitisation and wheeze (area under the curve (AUC) = 0.82, 95% CI: 0.76-0.88). u-EPX and allergic sensitisation alone had similar predictive power (AUC [95%CI]: 0.64 [0.58-0.71] and 0.65 [0.60-0.71]). The best performing classification model for asthma prediction among children with doctor-confirmed wheeze in the first 3 years included child's u-EPX and sensitisation at age 3 years, sex, gestational age and maternal atopy (AUC: 0.76, 95%CI: 0.67-0.85).

CONCLUSIONS

Early-life u-EPX may be a useful non-invasive marker for asthma prediction in adolescence.

Social inequalities in childhood asthma

Asthma is a complex, heterogeneous condition, broadly characterized by chronic airway inflammation with variable expiratory airflow limitation, but with several subtypes underpinned by different (although likely overlapping) pathological mechanisms. It is one of the most common chronic diseases of childhood and represents a significant cost for healthcare systems and affected families. Evidence suggests that a disproportionate proportion of this burden falls on families from disadvantaged socioeconomic circumstances (SECs). In this review, we describe the extent to which growing up in disadvantaged SECs is associated with an increased risk of childhood asthma diagnosis and asthma outcomes, including how this differs geographically and across different asthma subtypes. We also discuss the complex and interdependent mediating pathways that may link disadvantaged SECs with childhood asthma and asthma-related outcomes. In high-income countries (HICs), there is a fairly consistent association between growing up in disadvantaged SECs and increased prevalence of childhood asthma. However, evidence suggests that this social patterning differs across different asthma subtypes, with asthma phenotypes associated with disadvantaged SECs being less likely to be associated with atopy and more likely to begin in infancy and persist into adolescence. Disadvantaged SECs are also associated with worse asthma outcomes, which may contribute to the persistence of symptoms among disadvantaged children. In low- and middle-income countries (LMICs), the patterns are more variable and data more limited, but there is some evidence that disadvantaged SECs and atopic asthma are similarly negatively associated. There are also clear disparities in asthma outcomes, with LMICs having disproportionately high asthma-related morbidity and mortality, despite having lower asthma prevalence. A lack of accessibility to essential medication and appropriate care no doubt contributes to these disparities. The pathways leading to social inequalities in asthma are complex and interdependent, and as yet not fully understood. There is a clear need for further research into the relative importance of potential mediating pathways, including how these vary across the life course and across asthma subtypes. A stronger understanding of these pathways will help identify the most effective policy entry points for intervention, ultimately reducing inequalities across the life course.

European Respiratory Society statement on preschool wheezing disorders: updated definitions, knowledge gaps and proposed future research directions

Since the publication of the European Respiratory Society (ERS) task force reports on the management of preschool wheezing in 2008 and 2014, a large body of evidence has accumulated suggesting that the clinical phenotypes that were proposed (episodic (viral) wheezing and multiple-trigger wheezing) do not relate to underlying airway pathology and may not help determine response to treatment. Specifically, using clinical phenotypes alone may no longer be appropriate, and new approaches that can be used to inform clinical care are needed for future research. This ERS task force reviewed the literature published after 2008 related to preschool wheezing and has suggested that the criteria used to define wheezing disorders in preschool children should include age of diagnosis (0 to <6 years), confirmation of wheezing on at least one occasion, and more than one episode of wheezing ever. Furthermore, diagnosis and management may be improved by identifying treatable traits, including inflammatory biomarkers (blood eosinophils, aeroallergen sensitisation) associated with type-2 immunity and differential response to inhaled corticosteroids, lung function parameters and airway infection. However, more comprehensive use of biomarkers/treatable traits in predicting the response to treatment requires prospective validation. There is evidence that specific genetic traits may help guide management, but these must be adequately tested. In addition, the task force identified an absence of caregiver-reported outcomes, caregiver/self-management options and features that should prompt specialist referral for this age group. Priorities for future research include a focus on identifying 1) mechanisms driving preschool wheezing; 2) biomarkers of treatable traits and efficacy of interventions in those without allergic sensitisation/eosinophilia; 3) the need to include both objective outcomes and caregiver-reported outcomes in clinical trials; 4) the need for a suitable action plan for children with preschool wheezing; and 5) a definition of severe/difficult-to-treat preschool wheezing.

Association between polymorphisms on chromosome 17q12-q21 and rhinovirus-induced interferon responses

BACKGROUND

Single nucleotide polymorphisms (SNPs) in genes on chromosome 17q12-q21 are associated with childhood-onset asthma and rhinovirus-induced wheeze. There are few mechanistic data linking chromosome 17q12-q21 to wheezing illness.

OBJECTIVE

We investigated whether 17q12-q21 risk alleles were associated with impaired interferon responses to rhinovirus.

METHODS

In a population-based birth cohort of European ancestry, we stimulated peripheral blood mononuclear cells with rhinovirus A1 (RV-A1) and rhinovirus A16 (RV-A16) and measured IFN and IFN-induced C-X-C motif chemokine ligand 10 (aka IP10) responses in supernatants. We investigated associations between virus-induced cytokines and 6 SNPs in 17q12-q21. Bayesian profile regression was applied to identify clusters of individuals with different immune response profiles and genetic variants.

RESULTS

Five SNPs (in high linkage disequilibrium, r2 ≥ 0.8) were significantly associated with RV-A1-induced IFN-β (rs9303277, P = .010; rs11557467, P = .012; rs2290400, P = .006; rs7216389, P = .008; rs8079416, P = .005). A reduction in RV-A1-induced IFN-β was observed among individuals with asthma risk alleles. There were no significant associations for RV-A1-induced IFN-α or CXCL10, or for any RV-A16-induced IFN/CXCL10. Bayesian profile regression analysis identified 3 clusters that differed in IFN-β induction to RV-A1 (low, medium, high). The typical genetic profile of the cluster associated with low RV-A1-induced IFN-β responses was characterized by a very high probability of being homozygous for the asthma risk allele for all SNPs. Children with persistent wheeze were almost 3 times more likely to be in clusters with reduced/average RV-A1-induced IFN-β responses than in the high immune response cluster.

CONCLUSIONS

Polymorphisms on chromosome 17q12-q21 are associated with rhinovirus-induced IFN-β, suggesting a novel mechanism-impaired IFN-β induction-links 17q12-q21 risk alleles with asthma/wheeze.

Lung function trajectories from school age to adulthood and their relationship with markers of cardiovascular disease risk

RATIONALE

Lung function in early adulthood is associated with subsequent adverse health outcomes.

OBJECTIVES

To ascertain whether stable and reproducible lung function trajectories can be derived in different populations and investigate their association with objective measures of cardiovascular structure and function.

METHODS

Using latent profile modelling, we studied three population-based birth cohorts with repeat spirometry data from childhood into early adulthood to identify trajectories of forced expiratory volume in 1 s (FEV1)/forced vital capacity (FVC). We used multinomial logistic regression models to investigate early-life predictors of the derived trajectories. We then ascertained the extent of the association between the derived FEV1/FVC trajectories and blood pressure and echocardiographic markers of increased cardiovascular risk and stroke in ~3200 participants at age 24 years in one of our cohorts.

RESULTS

We identified four FEV1/FVC trajectories with strikingly similar latent profiles across cohorts (pooled N=6377): above average (49.5%); average (38.3%); below average (10.6%); and persistently low (1.7%). Male sex, wheeze, asthma diagnosis/medication and allergic sensitisation were associated with trajectories with diminished lung function in all cohorts. We found evidence of an increase in cardiovascular risk markers ascertained by echocardiography (including left ventricular mass indexed to height and carotid intima-media thickness) with decreasing FEV1/FVC (with p values for the mean crude effects per-trajectory ranging from 0.10 to p<0.001). In this analysis, we considered trajectories as a pseudo-continuous variable; we confirmed the assumption of linearity in all the regression models.

CONCLUSIONS

Childhood lung function trajectories may serve as predictors in the development of not only future lung disease, but also the cardiovascular disease and multimorbidity in adulthood.

Component-specific clusters for diagnosis and prediction of allergic airway diseases

BACKGROUND

Previous studies which applied machine learning on multiplex component-resolved diagnostics arrays identified clusters of allergen components which are biologically plausible and reflect the sources of allergenic proteins and their structural homogeneity. Sensitization to different clusters is associated with different clinical outcomes.

OBJECTIVE

To investigate whether within different allergen component sensitization clusters, the internal within-cluster sensitization structure, including the number of c-sIgE responses and their distinct patterns, alters the risk of clinical expression of symptoms.

METHODS

In a previous analysis in a population-based birth cohort, by clustering component-specific (c-s)IgEs, we derived allergen component clusters from infancy to adolescence. In the current analysis, we defined each subject's within-cluster sensitization structure which captured the total number of c-sIgE responses in each cluster and intra-cluster sensitization patterns. Associations between within-cluster sensitization patterns and clinical outcomes (asthma and rhinitis) in early-school age and adolescence were examined using logistic regression and binomial generalized additive models.

RESULTS

Intra-cluster sensitization patterns revealed specific associations with asthma and rhinitis (both contemporaneously and longitudinally) that were previously unseen using binary sensitization to clusters. A more detailed description of the subjects' within-cluster c-sIgE responses in terms of the number of positive c-sIgEs and unique sensitization patterns added new information relevant to allergic diseases, both for diagnostic and prognostic purposes. For example, the increase in the number of within-cluster positive c-sIgEs at age 5 years was correlated with the increase in prevalence of asthma at ages 5 and 16 years, with the correlations being stronger in the prediction context (e.g. for the largest 'Broad' component cluster, contemporaneous: r = .28, p = .012; r = .22, p = .043; longitudinal: r = .36, p = .004; r = .27, p = .04).

CONCLUSION

Among sensitized individuals, a more detailed description of within-cluster c-sIgE responses in terms of the number of positive c-sIgE responses and distinct sensitization patterns, adds potentially important information relevant to allergic diseases.

Understanding the heterogeneity of childhood allergic sensitization and its relationship with asthma

PURPOSE OF REVIEW

To review the current state of knowledge on the relationship between allergic sensitization and asthma; to lay out a roadmap for the development of IgE biomarkers that differentiate, in individual sensitized patients, whether their sensitization is important for current or future asthma symptoms, or has little or no relevance to the disease.

RECENT FINDINGS

The evidence on the relationship between sensitization and asthma suggests that some subtypes of allergic sensitization are not associated with asthma symptoms, whilst others are pathologic. Interaction patterns between IgE antibodies to individual allergenic molecules on component-resolved diagnostics (CRD) multiplex arrays might be hallmarks by which different sensitization subtypes relevant to asthma can be distinguished. These different subtypes of sensitization are associated amongst sensitized individuals at all ages, with different clinical presentations (no disease, asthma as a single disease, and allergic multimorbidity); amongst sensitized preschool children with and without lower airway symptoms, with different risk of subsequent asthma development; and amongst sensitized patients with asthma, with differing levels of asthma severity.

SUMMARY

The use of machine learning-based methodologies on complex CRD data can help us to design better diagnostic tools to help practising physicians differentiate between benign and clinically important sensitization.

Obstructive and restrictive spirometry from school age to adulthood: three birth cohort studies

Background

Spirometric obstruction and restriction are two patterns of impaired lung function which are predictive of poor health. We investigated the development of these phenotypes and their transitions through childhood to early adulthood.

Methods

In this study, we analysed pooled data from three UK population-based birth cohorts established between 1989 and 1995. We applied descriptive statistics, regression modelling and data-driven modelling to data from three population-based birth cohorts with at least three spirometry measures from childhood to adulthood (mid-school: 8-10 years, n = 8404; adolescence: 15-18, n = 5764; and early adulthood: 20-26, n = 4680). Participants were assigned to normal, restrictive, and obstructive spirometry based on adjusted regression residuals. We considered two transitions: from 8-10 to 15-18 and from 15-18 to 20-26 years.

Findings

Obstructive phenotype was observed in ∼10%, and restrictive in ∼9%. A substantial proportion of children with impaired lung function in school age (between one third in obstructive and a half in restricted phenotype) improved and achieved normal and stable lung function to early adulthood. Of those with normal lung function in school-age, <5% declined to adulthood. Underweight restrictive and obese obstructive participants were less likely to transit to normal. Maternal smoking during pregnancy and current asthma diagnosis increased the risk of persistent obstruction and worsening. Significant associate of worsening in restrictive phenotypes was lower BMI at the first lung function assessment. Data-driven methodologies identified similar risk factors for obstructive and restrictive clusters.

Interpretation

The worsening and improvement in obstructive and restrictive spirometry were observed at all ages. Maintaining optimal weight during childhood and reducing maternal smoking during pregnancy may reduce spirometry obstruction and restriction and improve lung function.

Funding

MRC Grant MR/S025340/1.

Genetics of preschool wheeze and its progression to childhood asthma

Wheezing is a common and heterogeneous condition in preschool children. In some countries, the prevalence can be as high as 30% and up to 50% of all children experience wheezing before the age of 6. Asthma often starts with preschool wheeze, but not all wheezing children will develop asthma at school age. At this moment, it is not possible to accurately predict which wheezing children will develop asthma. Recently, studying the genetics of wheeze and the childhood-onset of asthma have grown in interest. Childhood-onset asthma has a stronger heritability in comparison with adult-onset asthma. In early childhood asthma exacerbations, CDHR3, which encodes the receptor for Rhinovirus C, was identified, as well as IL33, and the 17q locus that includes GSDMB and ORMDL3 genes. The 17q locus is the strongest wheeze and childhood-onset asthma locus, and was shown to interact with many environmental factors, including smoking and infections. Finally, ANXA1 was recently associated with early-onset, persistent wheeze. ANXA1 may help resolve eosinophilic inflammation. Overall, despite its complexities, genetic approaches to unravel the early-onset of wheeze and asthma are promising, since these shed more light on mechanisms of childhood asthma-onset. Implicated genes point toward airway epithelium and its response to external factors, such as viral infections. However, the heterogeneity of wheeze phenotypes complicates genetic studies. It is therefore important to define accurate wheezing phenotypes and forge larger international collaborations to gain a better understanding of the pathways underlying early-onset asthma.

Identification of eczema clusters and their association with filaggrin and atopic comorbidities: analysis of five birth cohorts

BACKGROUND

Longitudinal modelling of the presence/absence of current eczema through childhood has identified similar phenotypes, but their characteristics often differ between studies.

OBJECTIVES

To demonstrate that a more comprehensive description of longitudinal pattern of symptoms may better describe trajectories than binary information on eczema presence.

METHODS

We derived six multidimensional variables of eczema spells from birth to 18 years of age (including duration, temporal sequencing and the extent of persistence/recurrence). Spells were defined as consecutive observations of eczema separated by no eczema across 5 epochs in five birth cohorts: infancy (first year); early childhood (age 2-3 years); preschool/early school age (4-5 years); middle childhood (8-10 years); adolescence (14-18 years). We applied Partitioning Around Medoids clustering on these variables to derive clusters of the temporal patterns of eczema. We then investigated the stability of the clusters, within-cluster homogeneity and associated risk factors, including FLG mutations.

RESULTS

Analysis of 7464 participants with complete data identified five clusters: (i) no eczema (51.0%); (ii) early transient eczema (21.6%); (iii) late-onset eczema (LOE; 8.1%); (iv) intermittent eczema (INT; 7.5%); and (v) persistent eczema (PE; 11.8%). There was very-high agreement between the assignment of individual children into clusters when using complete or imputed (n = 15 848) data (adjusted Rand index = 0.99; i.e. the clusters were very stable). Within-individual symptom patterns across clusters confirmed within-cluster homogeneity, with consistent patterns of symptoms among participants within each cluster and no overlap between the clusters. Clusters were characterized by differences in associations with risk factors (e.g. parental eczema was associated with all clusters apart from LOE; sensitization to inhalant allergens was associated with all clusters, with the highest risk in the PE cluster). All clusters apart from LOE were associated with FLG mutations. Of note, the strongest association was for PE [relative risk ratio (RRR) 2.70, 95% confidence interval (CI) 2.24-3.26; P < 0.001] followed by INT (RRR 2.29, 95% CI 1.82-2.88; P < 0.001).

CONCLUSIONS

Clustering of multidimensional variables identified stable clusters with different genetic architectures. Using multidimensional variables may capture eczema development and derive stable and internally homogeneous clusters. However, deriving homogeneous symptom clusters does not necessarily mean that these are underpinned by completely unique mechanisms.

Understanding progression from pre-school wheezing to school-age asthma: Can modern data approaches help?

Preschool wheezing and childhood asthma create a heavy disease burden which is only exacerbated by the complexity of the conditions. Preschool wheezing exhibits both "curricular" and "aetiological" heterogeneity: that is, heterogeneity across patients both in the time-course of its development and in its underpinning pathological mechanisms. Since these are not fully understood, but clinical presentations across patients may nonetheless be similar, current diagnostic labels are imprecise-not mapping cleanly onto underlying disease mechanisms-and prognoses uncertain. These uncertainties also make a identifying new targets for therapeutic intervention difficult. In the past few decades, carefully designed birth cohort studies have collected "big data" on a large scale, incorporating not only a wealth of longitudinal clinical data, but also detailed information from modalities as varied as imaging, multiomics, and blood biomarkers. The profusion of big data has seen the proliferation of what we term "modern data approaches" (MDAs)-grouping together machine learning, artificial intelligence, and data science-to make sense and make use of this data. In this review, we survey applications of MDAs (with an emphasis on machine learning) in childhood wheeze and asthma, highlighting the extent of their successes in providing tools for prognosis, unpicking the curricular heterogeneity of these conditions, clarifying the limitations of current diagnostic criteria, and indicating directions of research for uncovering the etiology of the diseases underlying these conditions. Specifically, we focus on the trajectories of childhood wheeze phenotypes. Further, we provide an explainer of the nature and potential use of MDAs and emphasize the scope of what we can hope to achieve with them.

Current state and prospects of artificial intelligence in allergy

The field of medicine is witnessing an exponential growth of interest in artificial intelligence (AI), which enables new research questions and the analysis of larger and new types of data. Nevertheless, applications that go beyond proof of concepts and deliver clinical value remain rare, especially in the field of allergy. This narrative review provides a fundamental understanding of the core concepts of AI and critically discusses its limitations and open challenges, such as data availability and bias, along with potential directions to surmount them. We provide a conceptual framework to structure AI applications within this field and discuss forefront case examples. Most of these applications of AI and machine learning in allergy concern supervised learning and unsupervised clustering, with a strong emphasis on diagnosis and subtyping. A perspective is shared on guidelines for good AI practice to guide readers in applying it effectively and safely, along with prospects of field advancement and initiatives to increase clinical impact. We anticipate that AI can further deepen our knowledge of disease mechanisms and contribute to precision medicine in allergy.

Childhood asthma phenotypes and endotypes: a glance into the mosaic

BACKGROUND

Asthma is an inflammatory lung disease that constitutes the most common noncommunicable chronic disease in childhood. Childhood asthma shows large heterogeneity regarding onset of disease, symptoms, severity, prognosis, and response to therapy.

MAIN BODY

Evidence suggests that this variability is due to distinct pathophysiological mechanisms, which has led to an exhaustive research effort to understand and characterize these distinct entities currently designated as "endotypes." Initially, studies focused on identifying specific groups using clinical variables yielding different "clinical phenotypes." In addition, the identification of specific patterns based on inflammatory cell counts and cytokine data has resulted in "inflammatory endotypes." More recently, an increasing number of molecular data from high-throughput technology ("omics" data) have allowed to investigate more complex "molecular endotypes."

CONCLUSION

A better definition and comprehension of childhood asthma heterogeneity is key for improving diagnosis and treatment. This review aims at summarizing the current knowledge on this topic and discusses some limitations in their application as well as recommendations for future studies.

Longitudinal Asthma Phenotypes from Childhood to Middle-Age: A Population-based Cohort Study

Rationale: Asthma is a heterogeneous condition, and longitudinal phenotyping may provide new insights into the origins and outcomes of the disease. Objectives: We aimed to characterize the longitudinal phenotypes of asthma between the first and sixth decades of life in a population-based cohort study. Methods: Respiratory questionnaires were collected at seven time points in the TAHS (Tasmanian Longitudinal Health Study) when participants were aged 7, 13, 18, 32, 43, 50, and 53 years. Current-asthma and ever-asthma status was determined at each time point, and group-based trajectory modeling was used to characterize distinct longitudinal phenotypes. Linear and logistic regression models were fitted to investigate associations of the longitudinal phenotypes with childhood factors and adult outcomes. Measurements and Main Results: Of 8,583 original participants, 1,506 had reported ever asthma. Five longitudinal asthma phenotypes were identified: early-onset adolescent-remitting (40%), early-onset adult-remitting (11%), early-onset persistent (9%), late-onset remitting (13%), and late-onset persistent (27%). All phenotypes were associated with chronic obstructive pulmonary disease at age 53 years, except for late-onset remitting asthma (odds ratios: early-onset adolescent-remitting, 2.00 [95% confidence interval (CI), 1.13-3.56]; early-onset adult-remitting, 3.61 [95% CI, 1.30-10.02]; early-onset persistent, 8.73 [95% CI, 4.10-18.55]; and late-onset persistent, 6.69 [95% CI, 3.81-11.73]). Late-onset persistent asthma was associated with the greatest comorbidity at age 53 years, with increased risk of mental health disorders and cardiovascular risk factors. Conclusions: Five longitudinal asthma phenotypes were identified between the first and sixth decades of life, including two novel remitting phenotypes. We found differential effects of these phenotypes on risk of chronic obstructive pulmonary disease and nonrespiratory comorbidities in middle age.

Phenotype and endotype based treatment of preschool wheeze

INTRODUCTION

Preschool wheeze (PSW) is a significant public health issue, with a high presentation rate to emergency departments, recurrent symptoms, and severe exacerbations. A heterogenous condition, PSW comprises several phenotypes that may relate to a range of pathobiological mechanisms. However, treating PSW remains largely generalized to inhaled corticosteroids and a short acting beta agonist, guided by symptom-based labels that often do not reflect underlying pathways of disease.

AREAS COVERED

We review the observable features and characteristics used to ascribe phenotypes in children with PSW and available pathobiological evidence to identify possible endotypes. These are considered in the context of treatment options and future research directions. The role of machine learning (ML) and modern analytical techniques to identify patterns of disease that distinguish phenotypes is also explored.

EXPERT OPINION

Distinct clusters (phenotypes) of severe PSW are characterized by different underlying mechanisms, some shared and some unique. ML-based methodologies applied to clinical, biomarker, and environmental data can help design tools to differentiate children with PSW that continues into adulthood, from those in whom wheezing resolves, identifying mechanisms underpinning persistence and resolution. This may help identify novel therapeutic targets, inform mechanistic studies, and serve as a foundation for stratification in future interventional therapeutic trials.

A meta-analysis of genome-wide association studies of childhood wheezing phenotypes identifies ANXA1 as a susceptibility locus for persistent wheezing

Background

Many genes associated with asthma explain only a fraction of its heritability. Most genome-wide association studies (GWASs) used a broad definition of 'doctor-diagnosed asthma', thereby diluting genetic signals by not considering asthma heterogeneity. The objective of our study was to identify genetic associates of childhood wheezing phenotypes.

Methods

We conducted a novel multivariate GWAS meta-analysis of wheezing phenotypes jointly derived using unbiased analysis of data collected from birth to 18 years in 9568 individuals from five UK birth cohorts.

Results

Forty-four independent SNPs were associated with early-onset persistent, 25 with pre-school remitting, 33 with mid-childhood remitting, and 32 with late-onset wheeze. We identified a novel locus on chr9q21.13 (close to annexin 1 [ANXA1], p<6.7 × 10-9), associated exclusively with early-onset persistent wheeze. We identified rs75260654 as the most likely causative single nucleotide polymorphism (SNP) using Promoter Capture Hi-C loops, and then showed that the risk allele (T) confers a reduction in ANXA1 expression. Finally, in a murine model of house dust mite (HDM)-induced allergic airway disease, we demonstrated that anxa1 protein expression increased and anxa1 mRNA was significantly induced in lung tissue following HDM exposure. Using anxa1-/- deficient mice, we showed that loss of anxa1 results in heightened airway hyperreactivity and Th2 inflammation upon allergen challenge.

Conclusions

Targeting this pathway in persistent disease may represent an exciting therapeutic prospect.

Funding

UK Medical Research Council Programme Grant MR/S025340/1 and the Wellcome Trust Strategic Award (108818/15/Z) provided most of the funding for this study.

What Have Mechanistic Studies Taught Us About Childhood Asthma?

Childhood asthma is a chronic heterogeneous syndrome consisting of different disease entities or phenotypes. The immunologic and cellular processes that occur during asthma development are still not fully understood but represent distinct endotypes. Mechanistic studies have examined the role of gene expression, protein levels, and cell types in early life development and the manifestation of asthma, many under the influence of environmental stimuli, which can be both protective and risk factors for asthma. Genetic variants can regulate gene expression, controlled partly by different epigenetic mechanisms. In addition, environmental factors, such as living space, nutrition, and smoking, can contribute to these mechanisms. All of these factors produce modifications in gene expression that can alter the development and function of immune and epithelial cells and subsequently different trajectories of childhood asthma. These early changes in a partially immature immune system can have dramatic effects (e.g., causing dysregulation), which in turn contribute to different disease endotypes and may help to explain differential responsiveness to asthma treatment. In this review, we summarize published studies that have aimed to uncover distinct mechanisms in childhood asthma, considering genetics, epigenetics, and environment. Moreover, a discussion of new, powerful tools for single-cell immunologic assays for phenotypic and functional analysis is included, which promise new mechanistic insights into childhood asthma development and therapeutic and preventive strategies.

Early childhood wheezing phenotypes and determinants in a South African birth cohort: longitudinal analysis of the Drakenstein Child Health Study

BACKGROUND

Developmental trajectories of childhood wheezing in low-income and middle-income countries (LMICs) have not been well described. We aimed to derive longitudinal wheeze phenotypes from birth to 5 years in a South African birth cohort and compare those with phenotypes derived from a UK cohort.

METHODS

We used data from the Drakenstein Child Health Study (DCHS), a longitudinal birth cohort study in a peri-urban area outside Cape Town, South Africa. Pregnant women (aged ≥18 years) were enrolled during their second trimester at two public health clinics. We followed up children from birth to 5 years to derive six multidimensional indicators of wheezing (including duration, temporal sequencing, persistence, and recurrence) and applied Partition Around Medoids clustering to derive wheeze phenotypes. We compared phenotypes with a UK cohort (the Avon Longitudinal Study of Parents and Children [ALSPAC]). We investigated associations of phenotypes with early-life exposures, including all-cause lower respiratory tract infection (LRTI) and virus-specific LRTI (respiratory syncytial virus, rhinovirus, adenovirus, influenza, and parainfluenza virus) up to age 5 years. We investigated the association of phenotypes with lung function at 6 weeks and 5 years.

FINDINGS

Between March 5, 2012, and March 31, 2015, we enrolled 1137 mothers and there were 1143 livebirths. Four wheeze phenotypes were identified among 950 children with complete data: never (480 children [50%]), early transient (215 children [23%]), late onset (104 children [11%]), and recurrent (151 children [16%]). Multivariate adjusted analysis indicated that LRTI and respiratory syncytial virus-LRTI, but not other respiratory viruses, were associated with increased risk of recurrent wheeze (odds ratio [OR] 2·79 [95% CI 2·05-3·81] for all LTRIs; OR 2·59 [1·30-5·15] for respiratory syncytial virus-LRTIs). Maternal smoking (1·88 [1·12-3·02]), higher socioeconomic status (2·46 [1·23-4·91]), intimate partner violence (2·01 [1·23-3·29]), and male sex (2·47 [1·50-4·04]) were also associated with recurrent wheeze. LRTI and respiratory syncytial virus-LRTI were also associated with early transient and late onset clusters. Wheezing illness architecture differed between DCHS and ALSPAC; children included in ALSPAC in the early transient cluster wheezed for a longer period before remission and late-onset wheezing started at an older age, and no persistent phenotype was identified in DCHS. At 5 years, airway resistance was higher in children with early or recurrent wheeze compared with children who had never wheezed. Airway resistance increased from 6 weeks to 5 years among children with recurrent wheeze.

INTERPRETATION

Effective strategies to reduce maternal smoking and psychosocial stressors and new preventive interventions for respiratory syncytial virus are urgently needed to optimise child health in LMICs.

FUNDING

UK Medical Research Council; The Bill & Melinda Gates Foundation; National Institutes of Health Human Heredity and Health in Africa; South African Medical Research Council; Wellcome Trust.

Asthma Management in Children

Asthma is a common, complex heterogeneous disease often beginning in early life and is characterized by reversible airflow obstruction. The phenotypic differences that exist in children with asthma may impact underlying comorbid conditions and pharmacologic treatment choices. Prenatal factors for increased risk of asthma could include maternal diet and the maternal microbiome. Evidence also suggests that postnatal microbial exposures and colonization contribute to the risk of allergic diseases and asthma. After confirming the diagnosis, asthma management in children centers on 3 broad areas: pharmacologic treatment, treatment of underlying comorbidities, and education of the patient and caregivers on the importance of adherence and device technique. Moreover, social determinants of health significantly impact on symptom burden and treatment response.

Evolution of Eczema, Wheeze, and Rhinitis from Infancy to Early Adulthood: Four Birth Cohort Studies

Rationale: The relationship between eczema, wheeze or asthma, and rhinitis is complex, and epidemiology and mechanisms of their comorbidities is unclear. Objectives: To investigate within-individual patterns of morbidity of eczema, wheeze, and rhinitis from birth to adolescence/early adulthood. Methods: We investigated onset, progression, and resolution of eczema, wheeze, and rhinitis using descriptive statistics, sequence mining, and latent Markov modeling in four population-based birth cohorts. We used logistic regression to ascertain if early-life eczema or wheeze, or genetic factors (filaggrin [FLG] mutations and 17q21 variants), increase the risk of multimorbidity. Measurements and Main Results: Single conditions, although the most prevalent, were observed significantly less frequently than by chance. There was considerable variation in the timing of onset/remission/persistence/intermittence. Multimorbidity of eczema+wheeze+rhinitis was rare but significantly overrepresented (three to six times more often than by chance). Although infantile eczema was associated with subsequent multimorbidity, most children with eczema (75.4%) did not progress to any multimorbidity pattern. FLG mutations and rs7216389 were not associated with persistence of eczema/wheeze as single conditions, but both increased the risk of multimorbidity (FLG by 2- to 3-fold, rs7216389 risk variant by 1.4- to 1.7-fold). Latent Markov modeling revealed five latent states (no disease/low risk, mainly eczema, mainly wheeze, mainly rhinitis, multimorbidity). The most likely transition to multimorbidity was from eczema state (0.21). However, although this was one of the highest transition probabilities, only one-fifth of those with eczema transitioned to multimorbidity. Conclusions: Atopic diseases fit a multimorbidity framework, with no evidence for sequential atopic march progression. The highest transition to multimorbidity was from eczema, but most children with eczema (more than three-quarters) had no comorbidities.