DETECÇÃO DE FRATURAS DO ESQUELETO APENDICULAR PEDIÁTRICO BASEADA EM INTELIGÊNCIA ARTIFICIAL: ESTUDO DE ACURÁCIA DIAGNÓSTICA

Abstract

Introduction: Pediatric fractures are among the leading causes of emergency department visits and are often difficult to diagnose due to the unique characteristics of the developing skeleton. In this context, artificial intelligence (AI) emerges as a promising tool to improve diagnostic accuracy and assist in the interpretation of radiographic examinations.Objectives: To evaluate the performance of artificial intelligence in detecting pediatric appendicular skeletal fractures, as well as to analyze its impact as a clinical decision-support tool.Methodology: This is a narrative literature review, with a search conducted in the PubMed, Embase, Scopus, Web of Science, and Cochrane Library databases, covering the period from 2022 to 2026. Studies evaluating AI algorithms applied to fracture detection in children were included, with analysis of outcomes such as sensitivity, specificity, and diagnostic accuracy.Results: The studies demonstrated that AI shows high diagnostic performance, with sensitivity and specificity comparable to or higher than those of healthcare professionals in certain contexts. Furthermore, the combined use of AI and medical evaluation resulted in a significant increase in diagnostic accuracy and a reduction in errors, especially among less experienced professionals. However, AI used in isolation still presents limitations, such as a higher occurrence of false negatives in some scenarios.Discussion: Despite advancements, the applicability of AI still faces challenges, including methodological heterogeneity, the need for external validation, and limitations related to pediatric anatomical variations.Conclusion: AI represents a promising complementary tool capable of improving the diagnosis of pediatric fractures; however, further studies are needed to ensure its safe and effective implementation.