USE OF MOBILE APPLICATIONS AND AI-POWERED TOOLS IN ALLERGY AND IMMUNOLOGY

Artificial intelligence (AI) and mobile health technologies are rapidly reshaping the landscape of al-lergology. Across diagnostic, monitoring, and therapeutic domains, AI-driven tools have demonstrated considerable potential in improving accuracy, efficiency, and personalization. In asthma management, machine learning algorithms integrate clinical, environmental, and sensor data to improve diagnostic accuracy, predict exacerbations, and stratify patient risk. In several studies, their performance was comparable to that of human experts. AI has also proven effective in assessing adherence to clinical guidelines and optimizing pediatric asthma care. In allergic rhinitis, AI models such as Long Short-Term Memory (LSTM) networks accurately predict patient flow and symptom patterns, supporting healthcare resource allocation. Digital health tools and mobile applications promote patient self-man-agement, real-time symptom tracking, and physician feedback. AI-powered biomarker discovery, in-cluding applications of next-generation sequencing (NGS), enables the development of personalized treatment strategies for allergic rhinitis. In chronic rhinosinusitis with nasal polyps (CRSwNP), con-volutional neural networks (CNNs) and deep learning techniques support automated image analysis, improve surgical planning, and help distinguish nasal polyps from other sinonasal lesions. Eosinophilic disorders benefit from AI-assisted endotyping that integrates omics and clinical data to support person-alized care. In eosinophilic esophagitis and eosinophilic granulomatosis with polyangiitis (EGPA), AI enhances diagnostic accuracy and facilitates treatment monitoring. For chronic spontaneous urticaria and angioedema, mobile health applications and AI algorithms enable symptom tracking, improve medication adherence, and provide early warnings of disease flare-ups. Automated evaluations of cur-rent apps highlight deficiencies in usability and clinical applicability, informing the development of more effective digital tools. In food allergy, AI-based models minimize the need for oral food challeng-es by integrating immune biomarkers with exposure history. Such systems also help identify shared therapeutic targets across food allergy, asthma, and eczema. Comprehensive reviews emphasize that integrating multi-omics data and predictive modeling is central to AI-driven personalized allergy care. In insect venom allergy, AI-enabled interpretation of component-resolved diagnostics supports the de-velopment of individualized immunotherapy. Additionally, population-level IgE profiling using AI im-proves transfusion safety and refines allergen risk assessment. AI is thus not a supplementary tool but a strategic driver of precision medicine in allergology. It bridges the gap between clinical complexity and actionable insights. Mobile health solutions improve accessibility and empower patients to engage in their care. Ethical implementation, transparency, and clinician collaboration remain essential. Future AI systems must address data standardization, validation, and equity. With continued innovation, AI is set to revolutionize allergy diagnosis, treatment, and prevention across the globe.