Developing an Effective Off-the-job Training Model and an Automated Evaluation System for Thoracoscopic Esophageal Atresia Surgery

In brief

This study describes development of a disease-specific training model for thoracoscopic esophageal atresia repair combined with an AI-powered automated evaluation system. Using deep learning to analyze instrument movements, the system provides objective skill assessment feedback to trainees, addressing the need for standardized competency evaluation in pediatric minimally invasive surgery.

• Disease-specific simulation models enable targeted skill acquisition for complex pediatric procedures like thoracoscopic EA repair.
• Deep learning can objectively assess surgical technique by analyzing instrument movement patterns during simulation training.
• Automated evaluation systems provide immediate, standardized feedback to trainees without requiring expert observer presence.
• Off-the-job training with objective metrics addresses the technical demands of pediatric minimally invasive surgery.
• AI-driven skill assessment may reduce subjectivity in surgical competency evaluation for rare congenital procedures.

Written by the GCMD Library team from the article.