ABSTRACT
Wheezing is a common condition in childhood, and its prevalence has increased in the last decade. Up to one-third of preschoolers develop recurrent wheezing, significantly impacting their quality of life and healthcare resources. Artificial Intelligence (AI) technologies have recently been applied in paediatric allergology and pulmonology, contributing to disease recognition, risk stratification, and decision support. Additionally, the COVID-19 pandemic has shaped healthcare systems, resulting in an increased workload and the necessity to reduce access to hospital facilities. In this view, AI and Machine Learning (ML) approaches can help address current issues in managing preschool wheezing, from its recognition with AI-augmented stethoscopes and monitoring with smartphone applications, aiming to improve parent-led/self-management and reducing economic and social costs. Moreover, in the last decade, ML algorithms have been applied in wheezing phenotyping, also contributing to identifying specific genes, and have been proven to even predict asthma in preschoolers. This minireview aims to update our knowledge on recent advancements of AI applications in childhood wheezing, summarizing and discussing the current evidence in recognition, diagnosis, phenotyping, and asthma prediction, with an overview of home monitoring and tele-management.
ABSTRACT
Asthma is a disease that has been described since the times of Hammurabi. However, it is only since the 1960s that effective therapeutic strategies have been available. Pathogenic mechanisms underlying the disease have been deeply studied, contributing to creating a "patient-specific asthma" definition. Biological drugs have been approved over the last twenty years, improving disease management in patients with severe asthma via a "precision medicine-driven approach". This article aims to describe the evolution of scientific knowledge in childhood asthma, focusing on the most recent biological therapies and their indications for patients with severe asthma.