AI-MRI V1.0
Research type
Research Study
Full title
DEVELOPING AN ARTIFICIAL INTELLIGENCE AUGMENTED DIAGNOSTIC IMAGING PATHWAY FOR PATIENTS WITH OCCULT SCAPHOID FRACTURES OF THE WRIST
IRAS ID
277447
Contact name
Alexia Karantana
Contact email
Sponsor organisation
University of Nottingham
Duration of Study in the UK
1 years, 9 months, 30 days
Research summary
Many patients come to Accident and Emergency (A&E) with wrist pain at the base of the thumb. This may be due to a bone called the scaphoid being broken or bruised. Unfortunately, not all breaks can be seen on initial A&E x-rays, so all patients are treated as if they have a broken bone. This includes immobilising the wrist and further appointments in fracture clinics and radiology, where the bone is re-assessed. It may take two or more weeks to be certain if the bone is broken or not. For most people, there is no break and the treatment is likely to have been unnecessary. However, given the long-term problems associated with missing a broken scaphoid, it is important patients are treated until we are certain.
We are investigating if a standard magnetic resonance imaging (MRI) scan and a computer can reliably identify a broken scaphoid, without repeated x-rays and appointments. We will use scans and clinical information to train a computer (artificial intelligence) how to identify broken scaphoids. To do this, we will obtain MRI scans from people with suspected breaks to be compared to normal scans, alongside x-rays and clinical information collected as part of routine care. MRI scans do not use x-ray radiation and are safe.
We plan to recruit 130 people with suspected or known scaphoid fractures in A&E or at their first appointment at the fracture clinic. Once they have consented to join our study, we will ask participants to undergo MRI scans of their wrists once, and to complete brief questionnaires at the start, 6 weeks and 3 months after their injury. We will also ask for their permission to review routine clinical information relating to their wrist. This will not affect, nor interfere with, the medical treatment they receive for their injury.REC name
West Midlands - Black Country Research Ethics Committee
REC reference
20/WM/0150
Date of REC Opinion
23 Jul 2020
REC opinion
Further Information Favourable Opinion