Project Summary The incidence of pediatric fractures is reported to be in the range of 12 to 36.1 per 1000 per year, with forearm fractures constituting approximately 40% of all long bone fractures. A timely and accurate diagnosis of forearm fractures is crucial to restore function and prevent complications such as persistent pain, stiffness, or growth plate arrest. The primary diagnostic approach involves physical examination and radiography. The treatment goal is to restore length and alignment between the distal and proximal bone fragments. While minimally displaced fractures may necessitate only immobilization for comfort through splinting or casting, moderately or severely displaced fractures often require reduction for realignment. Parents often take their children with suspected fractures to adult-based or urgent care medical centers, which lack the resources required for specialized pediatric care, leading to transfers to pediatric tertiary care centers and/or urgent consultations from pediatric orthopedic surgeons with specialized training in pediatric orthopedic injuries. To address and mitigate this healthcare burden, we propose the development of a machine learning framework named the Forearm Fracture AI-driven Recommendation System (FFAIRS) to improve forearm fracture management in pediatrics. Our primary goal is to leverage machine learning to generate recommendations for treating forearm fractures based on clinical presentation and x-ray analysis. Aim 1: Develop a machine learning framework for generating treatment recommendations for pediatric forearm fractures. Aim 2: Retrospectively evaluate FFAIRS for accurate prediction and improved patient outcomes.