The diagnostic accuracy of cross-sectional imaging for detecting acute scaphoid fractures in children: a systematic review

Objective: To determine the diagnostic accuracy of cross-sectional imaging for the diagnosis of acute scaphoid fractures in children. Methods: A systematic review of Medline, Embase and Cochrane databases between 1980 and July 2017 was independently performed by two observers. Criteria for study inclusion in a meta-analysis and assessment of the quality of such studies using the QADAS tool, were predetermined. Results: No studies were eligible for inclusion in a meta-analysis. Three studies (of low quality when assessed against the STARD guidelines for reporting of studies of diagnostic accuracy) assessed MRI (performed between Days 2 and 10 after acute injury) for the diagnosis of scaphoid fractures in a total of 119 children (age range 6 to 16 years). Study 1 (45 children) reported inter-observer reliability of radiographs and MRI of 0.53 and 0.95 respectively. Study 3 (18 children) reported a negative predictive value of MRI (even as early as Day 2), of 100%. No measure of diagnostic accuracy or observer reliability was reported in Study 2 (56 children). In all 3 studies, MRI identified more scaphoid fractures (and other carpal injuries) than radiographs. Study 3 showed that follow-up MRI between Days 38 and 45 added no new information compared to initial MRI. Conclusion: Based on a systematic review of the literature, there is currently no evidence on which to suggest an imaging protocol for suspected scaphoid fracture in children. Until such evidence is available, existing guidelines (which are based on findings from adult studies) should be followed. Advances in knowledge: (1) There is low quality evidence regarding the diagnostic accuracy of cross-sectional imaging for suspected scaphoid fractures in children and no evidence on which to propose an optimal imaging strategy. (2) Until such evidence is available, current guidelines (based predominantly on findings in adults and expert opinion) should be followed.