Document resource
Pediatric surgery is a highly specialized discipline dedicated to the diagnosis and surgical treatment of congenital or acquired diseases among neonates and children. 1 This field encompasses multiple highly specialized subspecialties, many of which involve rare or low-prevalence conditions, and clinical experiences are frequently concentrated in a small number of institutions.2 It is with these characteristics that the accurate identification of domain experts and informed allocation of academic resources is needed. With the advancement of artificial intelligence (AI), field-specific expert databases have increasingly been developed to support academic evaluation, reviewer selection, and strategic planning.3 Most existing systems rely on bibliometric indicators, rule-based matching, and natural language processing techniques.4 The pediatric surgery community is relatively small and highly subspecialized, with marked heterogeneity across disease areas, posing challenges for the development of a reliable and scalable expert database. Although AI tools have demonstrated potential in automating expert identification, extracting research interests, and mapping collaboration networks,5 6 existing approaches are still limited by fragmented data sources, author name ambiguity, and inconsistent affiliation metadata. Many available expert databases are designed for general biomedical fields and lack highly specialized clinical fields, including the pediatric surgery discipline.7 Furthermore, few systematic studies focus on long-term maintenance, update mechanisms, and integration with journal-level editorial workflows.