Artificial intelligence diagnostic accuracy in fracture detection from plain radiographs and comparing it with clinicians: a systematic review and meta-analysis

Easily missed pathologies of the musculoskeletal system in the emergency radiology setting

“…Applications of AI for image interpretation in the musculoskeletal region consist of the determination of body composition measurements, bone age, identification of fractures, screening for osteoporosis, evaluation of segmental spine pathology, detection and temporal monitoring of osseous metastases, diagnosis of primary bone and soft tissue tumors, and grading of osteoarthritis [44,45]. The number of publications per year in PubMed using the keywords ('artificial intelligence' and 'fracture' and 'radiology') has increased steadily from 30 publications in 2019 to 151 publications in 2023, and several AI algorithms, specifically deep learning algorithms, have been applied to fracture detection and classification, which are potentially helpful tools for radiologists and clinicians [46,47,48]. For instance, it has been reported that AI has the potential to automate and improve the accuracy of scaphoid fracture detection on radiography, thereby aiding in early diagnosis and reducing unnecessary clinical examinations, as well as reducing the risk of missed fractures and complications and reducing reading time and observer fatigue [49,50,51].…”