Thunderstorm-related respiratory symptoms: An old story with a new ending?Francis ThienProfessor/Director of Respiratory MedicineEastern Health & Monash University,Box Hill, Victoria 3128, AUSTRALIAIsabella Annesi-MaesanoProfessor of Environmental Epidemiology, INSERM Research Director,Department of Pulmonology, Allergy and Thoracic Oncology, University Hospital of Montpellier, Montpellier, FranceGennaro D’Amato,Director, Division of Respiratory and Allergic Diseases, High Speciality Hospital ‘A. Cardarelli’,Professor of Respiratory Allergy School of Specialization in Respiratory Diseases,Federico II University of Naples, Rione Sirignano 10,80121 Naples, Italy

Background: Serum allergen-specific immunoglobulins E (IgE) play a key role in allergy diagnosis along with clinical history and physical examination. Nowadays, allergen multiplex assays allow complex polyallergic cases to be solved as they assess up to 300 allergen-specific IgE. Recently, machine learning has emerged as a trending tool in medicine. The aim was to build a nationwide, open-access database to create an algorithm that could predict allergy diagnosis, severity, category (airborne, food, venom) and culprit allergens. Methods: A retrospective national database was created by the French Society of Allergology in collaboration with AllergoBioNet and the Health Data Hub. Collected data were de-identified patient profiles with five demographic items, twenty clinical items and sIgE results of one allergen multiplex assay. An international crowdsourced machine learning competition was hosted by the Trustii.io platform. Criteria for algorithm evaluation were the F-score (a measure of a model’s accuracy on a dataset) and external validation on patient profiles outside the database (80%-20%, respectively). Results: Data were collected from 4271 patient files. Two hundred and ninety-two data scientists competed with 3135 algorithms. The best F-scores were comprised between 78% and 80%. Models associated with the highest F-scores used gradient boosting classifiers such as LightGBM, CatBoost, XGBoost adapted for tabular datasets with categorical features. Conclusions: We report here the first artificial intelligence models applied to allergen multiplex arrays interpretation in a nationwide real-world database built to be open access. With F-scores close to 80%, the French Allergen Chip Challenge paves the way for a diagnostic prediction tool for practicing allergists.

Humans inhale, ingest and touch thousands of fungi each day. The ubiquity and diversity of the fungal kingdom are in sharp contrast with their complex and relatively blurred taxonomy and scarce knowledge about their distribution, pathogenic effects, and effective interventions at the environmental and individual levels. Here, we present an overview of salient features of fungi as permanent players of the human exposome and key determinants of human health. Improved understanding of the fungal exposome sheds new light on the epidemiology of fungal-related diseases, their immunological substratum, the currently available methods, and biomarkers for environmental and medical fungi. Unmet needs are described and potential approaches are highlighted as perspectives.

Background: Allergic rhinitis (AR) is a major non-communicable disease that affects the health-related quality of life (HRQoL) of patients. AR is significantly related to asthma also affecting HRQoL. However, data on HRQoL and symptom control in AR patients with comorbid asthma are lacking. Objective: To assess the differences of symptom control and HRQoL in AR patients with and without comorbid asthma. Methods: In this multicentre, cross-sectional study, patients with AR were screened and administered questionnaires of demographic characteristics and health conditions (symptoms/diagnosis of AR and asthma, disease severity level, and allergic conditions). HRQoL was assessed using a modified version of the RHINASTHMA questionnaire and symptom control was evaluated by a modified version of the Control of Allergic Rhinitis/Asthma Test (CARAT). Results: Out of 643 patients with AR, 500 (78%) had asthma as a comorbidity, and 54% had moderate-severe intermittent AR, followed by moderate-severe persistent AR (34%). Patients with both AR and asthma had significantly higher RHINASTHMA scores than the patients with AR alone (e.g., median RHINASTHMA-total score 84 vs. 48.5, respectively). Conversely, CARAT scores were significantly lower in AR with comorbid asthma than in the patients with AR alone (median CARAT-total score 16.5 vs. 23, respectively). Upon stratifying asthma based on severity, AR patients with severe persistent asthma had worse HRQoL and control than AR patients with mild persistent asthma. Conclusions: Our observation of poorer HRQoL and symptoms control in AR patients with comorbid asthma supports the importance of a comprehensive approach for the management of AR in case of a comorbid allergic condition.

A document by Isabella Annesi. Click on the document to view its contents.

A document by Isabella Annesi. Click on the document to view its contents.

The International Classification of Diseases (ICD) provides a common language for use worldwide as a diagnostic and classification tool for epidemiology, clinical purposes and health management. Since its first edition, the ICD has maintained a framework distributing conditions according to topography, with the result that some complex conditions, such as allergies and hypersensitivity disorders (A/H) including anaphylaxis, have been poorly represented. The change in hierarchy in ICD-11 permitted the construction of the pioneer section addressed to A/H, which may result in more accurate mortality and morbidity statistics, including more accurate accounting for mortality due to anaphylaxis, strengthen classification, terminology and definitions. The ICD-11 was presented and adopted by the 72nd World Health Assembly in May 2019 and the implementation is ongoing worldwide. We here present the outcomes from an online survey undertaken to reach out the allergy community worldwide in order to peer review the terminology, classification and definitions of A/H introduced into ICD-11 and to support their global implementation. Data are presented here for 406 respondents from 74 countries. All of the sub-sections of the new A/H section of the ICD-11 had been considered with good accuracy by the majority of respondents. We believe that, in addition to help during the implementation phase, all the comments provided will help to improve the A/H classification and to increase awareness by different disciplines of what actions are needed to ensure more accurate epidemiological data and better clinical management of A/H patients.