Patients undergoing X-ray for suspected fracture in the emergency department or minor injuries unit Injury, Occupational Diseases, Poisoning
Conditions
Interventions
The trial will involve installing a MHRA- and CE-approved AI fracture detection software at each site for 6 months. Clinicians will be able to view AI annotated images to aid in diagnosis when reviewi
Sponsors
Oxford University Hospitals NHS Trust
Eligibility
Sex/Gender
All
Age
2 Years to 100 Years
Inclusion criteria
Inclusion criteria: All patients undergoing X-Rays in ED or MIU for a suspected fracture will be eligible for inclusion
Exclusion criteria
Exclusion criteria: 1. Patients under 2 years old 2. Skeletal survey conducted to assess for non-accidental injury 3. Skull, facial bone, dental, and cervical spine X-rays 4. Thoracolumbar spine X-rays in patients under 18 years old 5. Patient has opted out of data sharing on the National Data Opt-Out 6. Patient completes the opt out questionnaire displayed on posters in the waiting room
Design outcomes
Primary
| Measure | Time frame |
|---|---|
| Unnecessary NHS contacts measured via electronic patient record audit of composite endpoints (phone consultations, repeat ED attendances, additional imaging, GP consultations, late fracture clinic referrals, inappropriate early clinical use, unnecessary imaging, immobilization, and sick leave) compared between periods when AI system is active ("On") versus inactive ("Off") throughout the entire 6-month study period (December 2025 – May 2026), with comparison occurring monthly during the alternating On/Off periods. | — |
Secondary
| Measure | Time frame |
|---|---|
| Patient Impact: 1. False negative fracture detection rate measured by comparison of AI algorithm output versus final radiology report at each X-ray during AI "On" periods (December 2025 – May 2026) 2. False positive fracture detection rate measured by comparison of AI algorithm output versus final radiology report at each X-ray during AI "On" periods (December 2025 – May 2026) 3. Number of inappropriate interventions (unnecessary treatments/referrals) measured via electronic patient record audit comparing AI "On" versus AI "Off" periods throughout the 6-month study period 4. Patient-reported outcomes measured using the EQ-5D questionnaire at 1 month post-initial ED/MIU presentation (December 2025 – May 2026) Clinician Impact: 1. Clinician satisfaction and confidence with the AI tool measured using a 5-point Likert scale questionnaire at baseline (December 2025) and 6 months (May 2026) Service Impact: 1. Number of patients referred to Fracture Clinic from ED/MIU measured via electronic patient record and RIS audit comparing AI "On" versus AI "Off" periods throughout the 6-month study period 2. Number of patients admitted to hospital with suspected fractures measured via electronic patient record audit comparing AI "On" versus AI "Off" periods throughout the 6-month study period 3. Number of patients recalled to ED due to missed fractures (false negatives) measured via electronic patient record audit comparing AI "On" versus AI "Off" periods throughout the 6-month study period 4. Number of unplanned reattendances for the same injury measured via electronic patient record audit comparing AI "On" versus AI "Off" periods throughout the 6-month study period 5. Length of Stay (LoS) in ED/MIU for patients with suspected fractures (measured in minutes from registration to discharge) via electronic patient record audit comparing AI "On" versus AI "Off" periods at each patient visit throughout the 6-month study period Technical Performance: 1. Sensitivity and specificity of | — |
Countries
England, United Kingdom
Contacts
Public ContactAlex Novak
Outcome results
None listed