Child abuse and neglect are globally prevalent issues with serious long-term consequences. Early identification of at-risk children is critical for effective intervention and rehabilitation. In recent years, artificial intelligence (AI)-assisted tools have begun to be explored for their potential in detecting child abuse and neglect. However, research on AI-supported fracture imaging in this context remains scarce. This study aimed to evaluate the limited number of existing studies and offer insights into future directions for research in this field. 

A comprehensive literature search was conducted across PubMed, EMBASE, and Google Scholar databases for studies published up to March 2025. The review focused on AI-supported fracture imaging related to child abuse and neglect. Out of 165 studies initially identified, data from 5 relevant studies were included— specifically, two focused on clavicle fractures, two on rib fractures, and one on distal tibial metaphyseal fractures. Although the rib fracture studies included children under two years of age, most cases involved imaging from the neonatal period. 

Orthopedics and traumatology play a pivotal role in the detection of child abuse and neglect through radiographic assessment. Specific radiological features have been identified to help differentiate fractures due to abuse from those resulting from accidental trauma. AI-driven algorithms capable of predicting the likelihood of abuse-related fractures on radiographs may significantly aid in identifying neglected cases. Nevertheless, current research in this area remains limited. 

In conclusion, despite its widespread prevalence, child abuse and neglect continue to be underdetected. AI-based radiographic tools show promise in improving diagnostic accuracy, particularly within orthopedic and trauma settings. Expanding research in this field-across various fracture types and age groups-will be essential to enhance the clinical utility of AI in the early detection and management of child abuse and neglect.