Diagnosis of suspected scaphoid fractures

Paul HC Stirling, Jason A Strelzow, Job N Doornberg, Timothy O. White, Margaret M McQueen, Andrew Duckworth

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

• Suspected scaphoid fractures are a diagnostic and therapeutic challenge, despite advances in knowledge and imaging. The risks and restrictions of routine immobilisation and restriction of activities in a young and active population must be weighed against the risks of non-union associated with a missed fracture.
• The prevalence of true fractures amongst suspected fractures is low. This greatly reduces the statistical probability that a positive diagnostic test will correspond with a true fracture, reducing the positive predictive value of an investigation.
• There is no consensus reference standard for a true fracture and thus alternative statistical methods for calculating sensitivity, specificity, positive and negative predictive value are required.
• Clinical prediction rules incorporating a set of demographic and clinical factors may allow stratification of secondary imaging, which could in turn increase the pre-test probability of a scaphoid fracture and improve the diagnostic performance of the sophisticated radiological investigations available.
• Machine learning (ML) derived probability calculators may augment risk stratification, and can improve through self-learning, although these theoretical benefits need further prospective evaluation.
• Convolutional neural networks (CNN) are a form of Artificial Intelligence (AI) that have demonstrated great promise in the recognition of scaphoid fractures on plain radiographs. However, in the more challenging diagnostic scenario of a suspected or so-called “clinical” scaphoid fracture CNNs have not yet proven superior over a diagnosis made by experienced surgeons.
Original languageEnglish
Article numbere20.00247
JournalJournal of Bone and Joint Surgery
Issue number12
Publication statusPublished - 1 Dec 2021


Dive into the research topics of 'Diagnosis of suspected scaphoid fractures'. Together they form a unique fingerprint.

Cite this