Dr. Prav Hamal is a UK paediatric trainee, clinical educator, and researcher with academic distinctions from the University of Bristol and Cardiff University. He has worked across multiple NHS specialties including paediatrics, emergency medicine, surgery, gastroenterology, and neonatology. Alongside his clinical training, he is actively involved in medical education, leadership, and international mentorship, and has received several national awards for research and presentations. His interests include paediatric emergency medicine, surgical outcomes, health inequalities, and doctor wellbeing.        

Artificial Intelligence in Paediatric Allergy: Current Applications and Future Directions     Background: Paediatric allergic disease has increased significantly over the past decade, placing growing pressure on healthcare systems. Diagnosis relies on clinical history supported by imperfect tests such as serum-specific IgE and skin prick testing, often leading to overdiagnosis and unnecessary dietary restriction. Over the last 10 years, artificial intelligence (AI) has emerged as a potential tool to improve diagnostic accuracy, risk stratification, and patient education in allergy care.     Aim: To review developments in AI applications in paediatric allergy over the past decade (2015–2025) and explore its future role in improving diagnosis, management, and healthcare efficiency.     Method: A narrative literature review was conducted using PubMed, MEDLINE, and Google Scholar. Studies published between 2015 and 2025 were identified using keywords including “paediatric allergy,” “artificial intelligence,” “machine learning,” “food allergy,” and “anaphylaxis.” Relevant original studies, systematic reviews, and clinical commentaries were included.     Results: AI applications in paediatric allergy have evolved over the past decade across three key domains: Diagnosis and risk prediction: Machine learning models integrating clinical history, IgE levels, and component-resolved diagnostics have demonstrated improved accuracy compared to traditional diagnostic approaches, with a focus on reducing false-positive allergy diagnoses. Clinical decision support: Recent developments include AI-assisted tools to differentiate allergic from non-allergic conditions (e.g. viral exanthems), and to support safer prescribing through identification of low-risk drug allergies. Digital health and patient engagement: AI-enabled platforms and mobile applications have emerged to support self-management, including anaphylaxis recognition and adherence to adrenaline auto-injector use, although paediatric-specific evidence remains limited. Despite progress, most applications remain in early validation stages with limited integration into routine clinical care.     Conclusion; Over the past decade, AI has shown significant potential to transform paediatric allergy care. While advances in diagnostic modelling and digital health are promising, further large-scale validation, real-world implementation, and consideration of ethical and equity issues are required before widespread adoption.