Using informatics to understand pediatric allergic diseases

Recent advances in the power, utility, and accessibility of artificial intelligence (AI) have enabled new methods of investigation in the biomedical sciences and opportunities to transform clinical workflows. As allergic conditions are among the most common chronic diseases affecting children, pediatric allergy represents a promising area for AI-augmented informatics methods to support molecular discovery, early identification, risk stratification, treatment customization, and longitudinal monitoring, as reviewed herein.

Recent pediatric allergy studies have applied informatics and AI methodologies across various data sources, including molecular and multiomic data, structured and unstructured electronic health record data, environmental exposures, diagnostic images, remote monitoring devices, and patient- and clinician-facing AI tools. Primarily still in the research phase, these approaches include biomarker discovery, disease phenotyping, risk stratification, prediction modeling, remote monitoring, and emerging chatbots for allergy education.

Although still relatively nascent within pediatric allergy, AI-augmented informatics shows promise for extracting usable information from complex data and developing tools aimed at personalizing disease detection and management. Most applications remain investigational, and continued progress will require transparency, rigorous validation, generalizability across diverse populations and health systems, feasibility of workflow integration, privacy protection, and longitudinal oversight to ensure continued safety and effectiveness.