Exploring the role of imaging, clinical scoring systems, and artificial intelligence in the diagnosis of pediatric appendicitis.
Authors
Affiliations (3)
Affiliations (3)
- University of Texas Southwestern, Department of Surgery, Dallas, Texas, United States.
- University of Texas Southwestern, Department of Surgery, Dallas, Texas, United States. Electronic address: [email protected].
- Children's Medical Center Dallas, Department of Surgery, Dallas, Texas, United States.
Abstract
Diagnostic evaluation of pediatric appendicitis relies on a combination of clinical assessment, imaging, and risk stratification tools. Imaging tools such as ultrasound, computed tomography, and magnetic resonance imaging differ in their accuracy, cost, radiation exposure, and operator dependence. Clinical scoring systems attempt to eliminate the subjectivity experienced with imaging but demonstrate variable performance in pediatric populations. Recent advances in artificial intelligence aim to improve diagnostic accuracy through integration of clinical, laboratory, and imaging data, demonstrating performance that equals or exceeds traditional scoring systems and may improve data interpretation, particularly in resource-limited settings. This review summarizes current evidence regarding imaging modalities, clinical scoring systems, and artificial intelligence applications in pediatric appendicitis. Continued optimization of ultrasound-based pathways and thoughtful integration of AI-driven decision-support tools may improve diagnostic accuracy while minimizing unnecessary radiation exposure and delays in care.