Generative models improve fairness of medical classifiers under distribution shifts.

Domain generalization is a ubiquitous challenge for machine learning in healthcare. Model performance in real-world conditions might be lower than expected because of discrepancies between the data encountered during deployment and development. Underrepresentation of some groups or conditions during model development is a common cause of this phenomenon. This challenge is often not readily addressed by targeted data acquisition and 'labeling' by expert clinicians, which can be prohibitively expensive or practically impossible because of the rarity of conditions or the available clinical expertise. We hypothesize that advances in generative artificial intelligence can help mitigate this unmet need in a steerable fashion, enriching our training dataset with synthetic examples that address shortfalls of underrepresented conditions or subgroups. We show that diffusion models can automatically learn realistic augmentations from data in a label-efficient manner. We demonstrate that learned augmentations make models more robust and statistically fair in-distribution and out of distribution. To evaluate the generality of our approach, we studied three distinct medical imaging contexts of varying difficulty: (1) histopathology, (2) chest X-ray and (3) dermatology images. Complementing real samples with synthetic ones improved the robustness of models in all three medical tasks and increased fairness by improving the accuracy of clinical diagnosis within underrepresented groups, especially out of distribution.

Deep learning for the prediction of clinical outcomes in internet-delivered CBT for depression and anxiety.

In treating depression and anxiety, just over half of all clients respond. Monitoring and obtaining early client feedback can allow for rapidly adapted treatment delivery and improve outcomes. This study seeks to develop a state-of-the-art deep-learning framework for predicting clinical outcomes in internet-delivered Cognitive Behavioural Therapy (iCBT) by leveraging large-scale, high-dimensional time-series data of client-reported mental health symptoms and platform interaction data. We use de-identified data from 45,876 clients on SilverCloud Health, a digital platform for the psychological treatment of depression and anxiety. We train deep recurrent neural network (RNN) models to predict whether a client will show reliable improvement by the end of treatment using clinical measures, interaction data with the iCBT program, or both. Outcomes are based on total improvement in symptoms of depression (Patient Health Questionnaire-9, PHQ-9) and anxiety (Generalized Anxiety Disorder-7, GAD-7), as reported within the iCBT program. Using internal and external datasets, we compare the proposed models against several benchmarks and rigorously evaluate them according to their predictive accuracy, sensitivity, specificity and AUROC over treatment. Our proposed RNN models consistently predict reliable improvement in PHQ-9 and GAD-7, using past clinical measures alone, with above 87% accuracy and 0.89 AUROC after three or more review periods, outperforming all benchmark models. Additional evaluations demonstrate the robustness of the achieved models across (i) different health services; (ii) geographic locations; (iii) iCBT programs, and (iv) client severity subgroups. Results demonstrate the robust performance of dynamic prediction models that can yield clinically helpful prognostic information ready for implementation within iCBT systems to support timely decision-making and treatment adjustments by iCBT clinical supporters towards improved client outcomes.

The promise of machine learning in predicting treatment outcomes in psychiatry.

For many years, psychiatrists have tried to understand factors involved in response to medications or psychotherapies, in order to personalize their treatment choices. There is now a broad and growing interest in the idea that we can develop models to personalize treatment decisions using new statistical approaches from the field of machine learning and applying them to larger volumes of data. In this pursuit, there has been a paradigm shift away from experimental studies to confirm or refute specific hypotheses towards a focus on the overall explanatory power of a predictive model when tested on new, unseen datasets. In this paper, we review key studies using machine learning to predict treatment outcomes in psychiatry, ranging from medications and psychotherapies to digital interventions and neurobiological treatments. Next, we focus on some new sources of data that are being used for the development of predictive models based on machine learning, such as electronic health records, smartphone and social media data, and on the potential utility of data from genetics, electrophysiology, neuroimaging and cognitive testing. Finally, we discuss how far the field has come towards implementing prediction tools in real-world clinical practice. Relatively few retrospective studies to-date include appropriate external validation procedures, and there are even fewer prospective studies testing the clinical feasibility and effectiveness of predictive models. Applications of machine learning in psychiatry face some of the same ethical challenges posed by these techniques in other areas of medicine or computer science, which we discuss here. In short, machine learning is a nascent but important approach to improve the effectiveness of mental health care, and several prospective clinical studies suggest that it may be working already.

A Machine Learning Approach to Understanding Patterns of Engagement With Internet-Delivered Mental Health Interventions.

Importance: The mechanisms by which engagement with internet-delivered psychological interventions are associated with depression and anxiety symptoms are unclear. Objective: To identify behavior types based on how people engage with an internet-based cognitive behavioral therapy (iCBT) intervention for symptoms of depression and anxiety. Design, Setting, and Participants: Deidentified data on 54 604 adult patients assigned to the Space From Depression and Anxiety treatment program from January 31, 2015, to March 31, 2019, were obtained for probabilistic latent variable modeling using machine learning techniques to infer distinct patient subtypes, based on longitudinal heterogeneity of engagement patterns with iCBT. Interventions: A clinician-supported iCBT-based program that follows clinical guidelines for treating depression and anxiety, delivered on a web 2.0 platform. Main Outcomes and Measures: Log data from user interactions with the iCBT program to inform engagement patterns over time. Clinical outcomes included symptoms of depression (Patient Health Questionnaire-9 [PHQ-9]) and anxiety (Generalized Anxiety Disorder-7 [GAD-7]); PHQ-9 cut point greater than or equal to 10 and GAD-7 scores greater than or equal to 8 were used to define depression and anxiety. Results: Patients spent a mean (SD) of 111.33 (118.92) minutes on the platform and completed 230.60 (241.21) tools. At baseline, mean PHQ-9 score was 12.96 (5.81) and GAD-7 score was 11.85 (5.14). Five subtypes of engagement were identified based on patient interaction with different program sections over 14 weeks: class 1 (low engagers, 19 930 [36.5%]), class 2 (late engagers, 11 674 [21.4%]), class 3 (high engagers with rapid disengagement, 13 936 [25.5%]), class 4 (high engagers with moderate decrease, 3258 [6.0%]), and class 5 (highest engagers, 5799 [10.6%]). Estimated mean decrease (SE) in PHQ-9 score was 6.65 (0.14) for class 3, 5.88 (0.14) for class 5, and 5.39 (0.14) for class 4; class 2 had the lowest rate of decrease at -4.41 (0.13). Compared with PHQ-9 score decrease in class 1, the Cohen d effect size (SE) was -0.46 (0.014) for class 2, -0.46 (0.014) for class 3, -0.61 (0.021) for class 4, and -0.73 (0.018) for class 5. Similar patterns were found across groups for GAD-7. Conclusions and Relevance: The findings of this study may facilitate tailoring interventions according to specific subtypes of engagement for individuals with depression and anxiety. Informing clinical decision needs of supporters may be a route to successful adoption of machine learning insights, thus improving clinical outcomes overall.

AI for social good: unlocking the opportunity for positive impact.

Advances in machine learning (ML) and artificial intelligence (AI) present an opportunity to build better tools and solutions to help address some of the world's most pressing challenges, and deliver positive social impact in accordance with the priorities outlined in the United Nations' 17 Sustainable Development Goals (SDGs). The AI for Social Good (AI4SG) movement aims to establish interdisciplinary partnerships centred around AI applications towards SDGs. We provide a set of guidelines for establishing successful long-term collaborations between AI researchers and application-domain experts, relate them to existing AI4SG projects and identify key opportunities for future AI applications targeted towards social good.

Early-life inhalant allergen exposure, filaggrin genotype, and the development of sensitization from infancy to adolescence.

BACKGROUND: We hypothesized that filaggrin (FLG) loss-of-function mutations modify the effect of allergen exposure on the development of allergic sensitization. OBJECTIVE: We sought to determine whether early-life exposure to inhalant allergens increases the risk of specific sensitization and whether FLG mutations modulate these odds. METHODS: In a population-based birth cohort we measured mite, cat, and dog allergen levels in dust samples collected from homes within the first year of life. Sensitization was assessed at 6 time points between infancy and age 16 years. Genotyping was performed for 6 FLG mutations. RESULTS: In the longitudinal multivariable model (age 1-16 years), we observed a significant interaction between FLG and Fel d 1 exposure on cat sensitization, with the effect of exposure being significantly greater among children with FLG mutations compared with those without (odds ratio, 1.36; 95% CI, 1.02-1.80; P = .035). The increase in risk of mite sensitization with increasing Der p 1 exposure was consistently greater among children with FLG mutations, but the interaction did not reach statistical significance. Different associations were observed for dogs: there was a significant interaction between FLG and dog ownership, but the risk of sensitization to any allergen was significantly lower among children with FLG mutations who were exposed to a dog in infancy (odds ratio, 0.16; 95% CI, 0.03-0.86; P = .03). CONCLUSIONS: FLG loss-of-function mutations modify the relationship between allergen exposure and sensitization, but effects differ at different ages and between different allergens.

Differential associations of allergic disease genetic variants with developmental profiles of eczema, wheeze and rhinitis.

BACKGROUND: Allergic diseases (eczema, wheeze and rhinitis) in children often present as heterogeneous phenotypes. Understanding genetic associations of specific patterns of symptoms might facilitate understanding of the underlying biological mechanisms. OBJECTIVE: To examine associations between allergic disease-related variants identified in a recent genome-wide association study and latent classes of allergic diseases (LCADs) in two population-based birth cohorts. METHODS: Eight previously defined LCADs between birth and 11 years: "No disease," "Atopic march," "Persistent eczema and wheeze," "Persistent eczema with later-onset rhinitis," "Persistent wheeze with later-onset rhinitis," "Transient wheeze," "Eczema only" and "Rhinitis only" were used as the study outcome. Weighted multinomial logistic regression was used to estimate associations between 135 SNPs (and a polygenic risk score, PRS) and LCADs among 6345 individuals from The Avon Longitudinal Study of Parents and Children (ALSPAC). Heterogeneity across LCADs was assessed before and after Bonferroni correction. Results were replicated in Manchester Asthma and Allergy Study (MAAS) (n = 896) and pooled in a meta-analysis. RESULTS: We found strong evidence for differential genetic associations across the LCADs; pooled PRS heterogeneity P-value = 3.3 × 10-14 , excluding "no disease" class. The associations between the PRS and LCADs in MAAS were remarkably similar to ALSPAC. Two SNPs (a protein-truncating variant in FLG and a SNP within an intron of GSDMB) had evidence for differential association (pooled P-values ≤ 0.006). The FLG locus was differentially associated across LCADs that included eczema, with stronger associations for LCADs with comorbid wheeze and rhinitis. The GSDMB locus in contrast was equally associated across LCADs that included wheeze. CONCLUSIONS AND CLINICAL RELEVANCE: We have shown complex, but distinct patterns of genetic associations with LCADs, suggesting that heterogeneous mechanisms underlie individual disease trajectories. Establishing the combination of allergic diseases with which each genetic variant is associated may inform therapeutic development and/or predictive modelling.

Temporal association of the development of oropharyngeal microbiota with early life wheeze in a population-based birth cohort.

BACKGROUND: A critical window in infancy has been proposed, during which the microbiota may affect subsequent health. The longitudinal development of the oropharyngeal microbiota is under-studied and may be associated with early-life wheeze. We aimed to investigate the temporal association of the development of the oropharyngeal microbiota with early-life wheeze. METHODS: A population-based birth cohort based in London, UK was followed for 24 months. We collected oropharyngeal swabs at six time-points. Microbiota was determined using sequencing of the V3-V5 region of the 16S rRNA-encoding gene. Medical records were reviewed for the outcome of doctor diagnosed wheeze. We used a time-varying model to investigate the temporal association between the development of microbiota and doctor-diagnosed wheeze. FINDINGS: 159 participants completed the study to 24 months and for 98 there was complete sequencing data at all timepoints and outcome data. Of these, 26 had doctor-diagnosed wheeze. We observed significant increase in the abundance of Neisseria between 9 and 24 months in children who developed wheeze (p = 0∙003), while in those without wheezing there was a significant increment in the abundance of Granulicatella (p = 0∙012) between 9 and 12 months, and of Prevotella (p = 0∙018) after 18 months. INTERPRETATION: A temporal association between the respiratory commensal Granulicatella and also Prevotella with wheeze (negative), and between Neisseria and wheeze (positive) was identified in infants prior to one year of age. This adds to evidence for the proposed role of the microbiota in the development of wheeze. FUND: Research funding from the Winnicott Foundation, Meningitis Now and Micropathology Ltd.

Individual risk assessment tool for school-age asthma prediction in UK birth cohort.

BACKGROUND: Current published asthma predictive tools have moderate positive likelihood ratios (+LR) but high negative likelihood ratios (-LR) based on their recommended cut-offs, which limit their clinical usefulness. OBJECTIVE: To develop a simple clinically applicable asthma prediction tool within a population-based birth cohort. METHOD: Children from the Manchester Asthma and Allergy Study (MAAS) attended follow-up at ages 3, 8 and 11 years. Data on preschool wheeze were extracted from primary-care records. Parents completed validated respiratory questionnaires. Children were skin prick tested (SPT). Asthma at 8/11 years (school-age) was defined as parentally reported (a) physician-diagnosed asthma and wheeze in the previous 12 months or (b) ≥3 wheeze attacks in the previous 12 months. An asthma prediction tool (MAAS APT) was developed using logistic regression of characteristics at age 3 years to predict school-age asthma. RESULTS: Of 336 children with physician-confirmed wheeze by age 3 years, 117(35%) had school-age asthma. Logistic regression selected 5 significant risk factors which formed the basis of the MAAS APT: wheeze after exercise; wheeze causing breathlessness; cough on exertion; current eczema and SPT sensitisation(maximum score 5). A total of 281(84%) children had complete data at age 3 years and were used to test the MAAS APT. Children scoring ≥3 were at high risk of having asthma at school-age (PPV > 75%; +LR 6.3, -LR 0.6), whereas children who had a score of 0 had very low risk(PPV 9.3%; LR 0.2). CONCLUSION: MAAS APT is a simple asthma prediction tool which could easily be applied in clinical and research settings.

Trajectories of childhood immune development and respiratory health relevant to asthma and allergy.

Events in early life contribute to subsequent risk of asthma; however, the causes and trajectories of childhood wheeze are heterogeneous and do not always result in asthma. Similarly, not all atopic individuals develop wheeze, and vice versa. The reasons for these differences are unclear. Using unsupervised model-based cluster analysis, we identified latent clusters within a prospective birth cohort with deep immunological and respiratory phenotyping. We characterised each cluster in terms of immunological profile and disease risk, and replicated our results in external cohorts from the UK and USA. We discovered three distinct trajectories, one of which is a high-risk 'atopic' cluster with increased propensity for allergic diseases throughout childhood. Atopy contributes varyingly to later wheeze depending on cluster membership. Our findings demonstrate the utility of unsupervised analysis in elucidating heterogeneity in asthma pathogenesis and provide a foundation for improving management and prevention of childhood asthma.

Lung function trajectories from pre-school age to adulthood and their associations with early life factors: a retrospective analysis of three population-based birth cohort studies.

BACKGROUND: Maximal lung function in early adulthood is an important determinant of mortality and COPD. We investigated whether distinct trajectories of lung function are present during childhood and whether these extend to adulthood and infancy. METHODS: To ascertain trajectories of FEV1, we studied two population-based birth cohorts (MAAS and ALSPAC) with repeat spirometry from childhood into early adulthood (1046 participants from 5-16 years and 1390 participants from 8-24 years). We used a third cohort (PIAF) with repeat lung function measures in infancy (V'maxFRC) and childhood (FEV1; 196 participants from 1 month to 18 years of age) to investigate whether these childhood trajectories extend from early life. We identified trajectories using latent profile modelling. We created an allele score to investigate genetic associations of trajectories, and constructed a multivariable model to identify their early-life predictors. FINDINGS: We identified four childhood FEV1 trajectories: persistently high, normal, below average, and persistently low. The persistently low trajectory (129 [5%] of 2436 participants) was associated with persistent wheezing and asthma throughout follow-up. In genetic analysis, compared with the normal trajectory, the pooled relative risk ratio per allele was 0·96 (95% CI 0·92-1·01; p=0·13) for persistently high, 1·01 (0·99-1·02; p=0·49) for below average, and 1·05 (0·98-1·13; p=0·13) for persistently low. Most children in the low V'maxFRC trajectory in infancy did not progress to the low FEV1 trajectory in childhood. Early-life factors associated with the persistently low trajectory included recurrent wheeze with severe wheezing exacerbations, early allergic sensitisation, and tobacco smoke exposure. INTERPRETATION: Reduction of childhood smoke exposure and minimisation of the risk of early-life sensitisation and wheezing exacerbations might reduce the risk of diminished lung function in early adulthood. FUNDING: None.

Evolution of IgE responses to multiple allergen components throughout childhood.

BACKGROUND: There is a paucity of information about longitudinal patterns of IgE responses to allergenic proteins (components) from multiple sources. OBJECTIVES: This study sought to investigate temporal patterns of component-specific IgE responses from infancy to adolescence, and their relationship with allergic diseases. METHODS: In a population-based birth cohort, we measured IgE to 112 components at 6 follow-ups during childhood. We used a Bayesian method to discover cross-sectional sensitization patterns and their longitudinal trajectories, and we related these patterns to asthma and rhinitis in adolescence. RESULTS: We identified 1 sensitization cluster at age 1, 3 at age 3, 4 at ages 5 and 8, 5 at age 11, and 6 at age 16 years. "Broad" cluster was the only cluster present at every follow-up, comprising components from multiple sources. "Dust mite" cluster formed at age 3 years and remained unchanged to adolescence. At age 3 years, a single-component "Grass" cluster emerged, which at age 5 years absorbed additional grass components and Fel d 1 to form the "Grass/cat" cluster. Two new clusters formed at age 11 years: "Cat" cluster and "PR-10/profilin" (which divided at age 16 years into "PR-10" and "Profilin"). The strongest contemporaneous associate of asthma at age 16 years was sensitization to dust mite cluster (odds ratio: 2.6; 95% CI: 1.2-6.1; P < .05), but the strongest early life predictor of subsequent asthma was sensitization to grass/cat cluster (odds ratio: 3.5; 95% CI: 1.6-7.4; P < .01). CONCLUSIONS: We describe the architecture of the evolution of IgE responses to multiple allergen components throughout childhood, which may facilitate development of better diagnostic and prognostic biomarkers for allergic diseases.

Cytokine Responses to Rhinovirus and Development of Asthma, Allergic Sensitization, and Respiratory Infections during Childhood.

RATIONALE: Immunophenotypes of antiviral responses, and their relationship with asthma, allergy, and lower respiratory tract infections, are poorly understood. OBJECTIVES: We characterized multiple cytokine responses of peripheral blood mononuclear cells to rhinovirus stimulation, and their relationship with clinical outcomes. METHODS: In a population-based birth cohort, we measured 28 cytokines after stimulation with rhinovirus-16 in 307 children aged 11 years. We used machine learning to identify patterns of cytokine responses, and related these patterns to clinical outcomes, using longitudinal models. We also ascertained phytohemagglutinin-induced T-helper cell type 2 (Th2)-cytokine responses (PHA-Th2). MEASUREMENTS AND MAIN RESULTS: We identified six clusters of children based on their rhinovirus-16 responses, which were differentiated by the expression of four cytokine/chemokine groups: interferon-related (IFN), proinflammatory (Inflam), Th2-chemokine (Th2-chem), and regulatory (Reg). Clusters differed in their clinical characteristics. Children with an IFNmodInflamhighestTh2-chemhighestReghighest rhinovirus-16-induced pattern had a PHA-Th2low response, and a very low asthma risk (odds ratio [OR], 0.08; 95% confidence interval [CI], 0.01-0.81; P = 0.03). Two clusters had a high risk of asthma and allergic sensitization, but with different trajectories from infancy to adolescence. The IFNlowestInflamhighTh2-chemlowRegmod cluster exhibited a PHA-Th2lowest response and was associated with early-onset asthma and sensitization, and the highest risk of asthma exacerbations (OR, 1.37; 95% CI, 1.07-1.76; P = 0.014) and lower respiratory tract infection hospitalizations (OR, 2.40; 95% CI, 1.26-4.58; P = 0.008) throughout childhood. In contrast, the IFNhighestInflammodTh2-chemmodReghigh cluster with a rhinovirus-16-cytokine pattern was characterized by a PHA-Th2highest response, and a low prevalence of asthma/sensitization in infancy that increased sharply to become the highest among all clusters by adolescence (but with a low risk of asthma exacerbations). CONCLUSIONS: Early-onset troublesome asthma with early-life sensitization, later-onset milder allergic asthma, and disease protection are each associated with different patterns of rhinovirus-induced immune responses.

Detection of IgE Reactivity to a Handful of Allergen Molecules in Early Childhood Predicts Respiratory Allergy in Adolescence.

BACKGROUND: Sensitization in early childhood may precede respiratory allergy in adolescence. METHODS: IgE reactivity against 132 allergen molecules was evaluated using the MeDALL microarray in sera obtained from a random sample of 786 children at the age of 4, 8 and 16years in a population based birth cohort (BAMSE). Symptoms were analyzed by questionnaire at ages 4, 8 and 16years. Clinically and independent relevant allergen molecules accounting for ≥90% of IgE reactivities in sensitized individuals and at all time-points were identified as risk molecules and used to predict respiratory allergy. The data was replicated in the Manchester Asthma and Allergy Study (MAAS) birth cohort by studying IgE reactivity with the use of a commercial IgE microarray. Sera were obtained from children at the ages of 3, 5, 8 and 11years (N=248) and the outcome was studied at 11years. FINDINGS: In the BAMSE cohort 4 risk molecules could be identified, i.e.: Ara h 1 (peanut), Bet v 1 (birch), Fel d 1 (cat), Phl p 1 (grass). For MAAS the corresponding number of molecules was 5: Der p 1 (dust mite), Der f 2 (dust mite), Phl p 1 (grass), Phl p 5 (grass), Fel d 1 (cat). In BAMSE, early IgE reactivity to ≥3 of 4 allergen molecules at four years predicted incident and persistent asthma and/or rhinitis at 16years (87% and 95%, respectively). The corresponding proportions in the MAAS cohort at 16years were 100% and 100%, respectively, for IgE reactivity to ≥3 of 5 risk molecules. INTERPRETATIONS: IgE reactivity to a few allergen molecules early in life identifies children with a high risk of asthma and/or rhinitis at 16years. These findings will be of importance for developing preventive strategies for asthma and rhinitis in children.

Asthma phenotypes in childhood.

INTRODUCTION: Asthma is no longer thought of as a single disease, but rather a collection of varying symptoms expressing different disease patterns. One of the ongoing challenges is understanding the underlying pathophysiological mechanisms that may be responsible for the varying responses to treatment. Areas Covered: This review provides an overview of our current understanding of the asthma phenotype concept in childhood and describes key findings from both conventional and data-driven methods. Expert Commentary: With the vast amounts of data generated from cohorts, there is hope that we can elucidate distinct pathophysiological mechanisms, or endotypes. In return, this would lead to better patient stratification and disease management, thereby providing true personalised medicine.

Disaggregating asthma: Big investigation versus big data.

We are facing a major challenge in bridging the gap between identifying subtypes of asthma to understand causal mechanisms and translating this knowledge into personalized prevention and management strategies. In recent years, "big data" has been sold as a panacea for generating hypotheses and driving new frontiers of health care; the idea that the data must and will speak for themselves is fast becoming a new dogma. One of the dangers of ready accessibility of health care data and computational tools for data analysis is that the process of data mining can become uncoupled from the scientific process of clinical interpretation, understanding the provenance of the data, and external validation. Although advances in computational methods can be valuable for using unexpected structure in data to generate hypotheses, there remains a need for testing hypotheses and interpreting results with scientific rigor. We argue for combining data- and hypothesis-driven methods in a careful synergy, and the importance of carefully characterized birth and patient cohorts with genetic, phenotypic, biological, and molecular data in this process cannot be overemphasized. The main challenge on the road ahead is to harness bigger health care data in ways that produce meaningful clinical interpretation and to translate this into better diagnoses and properly personalized prevention and treatment plans. There is a pressing need for cross-disciplinary research with an integrative approach to data science, whereby basic scientists, clinicians, data analysts, and epidemiologists work together to understand the heterogeneity of asthma.

Identification of Asthma Subtypes Using Clustering Methodologies.

Asthma is a heterogeneous disease comprising a number of subtypes which may be caused by different pathophysiologic mechanisms (sometimes referred to as endotypes) but may share similar observed characteristics (phenotypes). The use of unsupervised clustering in adult and paediatric populations has identified subtypes of asthma based on observable characteristics such as symptoms, lung function, atopy, eosinophilia, obesity, and age of onset. Here we describe different clustering methods and demonstrate their contributions to our understanding of the spectrum of asthma syndrome. Precise identification of asthma subtypes and their pathophysiological mechanisms may lead to stratification of patients, thus enabling more precise therapeutic and prevention approaches.

Age, sex and the association between skin test responses and IgE titres with asthma.

BACKGROUND: Skin prick tests (SPTs) and allergen-specific serum IgE (sIgE) measurements are the main diagnostic tools for confirming atopic sensitization. Results are usually reported as 'positive' or 'negative', using the same arbitrary cut-offs (SPT>3 mm, sIgE>0.35 kUA /l) across different ages and sexes. We investigated the influence of age and sex on the interpretation of allergy test in the context of childhood asthma. METHODS: In a population-based birth cohort (n = 1051), we ascertained the information on asthma/wheeze (validated questionnaires) and performed SPTs and sIgE measurement to inhalant allergens (dust mite, cat, dog) at follow-ups between ages three and 11 years. We investigated the association between quantitative sensitization (sum of SPT mean wheal diameters [MWD] and sIgE titres to the three allergens) and current wheeze and asthma across ages and sexes. RESULTS: We observed a significant association between the SPT MWD and sIgE titres and wheeze/asthma at most ages and for both sexes. However, the strength of this association was age- and sex-dependent. For SPTs, the strength of the association between MWD and asthma increased with increasing age; we observed the opposite pattern for sIgE titre. For any given SPT MWD/sIgE titre, boys were significantly more likely to express clinical symptoms, particularly in early life; this difference between males and females diminished with age and was no longer significant by age 11 years. CONCLUSIONS: Age and sex should be taken into account when interpreting the results of skin tests and sIgE measurement, and age- and sex-specific normative data are needed for these allergy tests.