Abstract
Introduction:
Radiology plays an integral role in fracture detection in the emergency department (ED). After hours, when there are fewer reporting radiologists, most radiographs are interpreted by ED physicians. A minority of these interpretations may miss diagnoses, which later require the callback of patients for further management. Artificial intelligence (AI) has been viewed as a potential solution to augment the shortage of radiologists after hours. We explored the efficacy of an AI solution in the detection of appendicular and pelvic fractures for adult radiographs performed after hours at a general hospital ED in Singapore, and estimated the potential monetary and non-monetary benefits.
Methods:
One hundred and fifty anonymised abnormal radiographs were retrospectively collected and fed through an AI fracture detection solution. The radiographs were re-read by two radiologist reviewers and their consensus was established as the reference standard. Cases were stratified based on the concordance between the AI solution and the reviewers’ findings. Discordant cases were further analysed based on the nature of the discrepancy into overcall and undercall subgroups. Statistical analysis was performed to evaluate the accuracy, sensitivity and inter-rater reliability of the AI solution.
AI solution
The software utilised was RBfracture (Radiobotics, Copenhagen, Denmark), a commercially available CE Class IIa AI fracture detection solution, which had been trained on over 200,000 radiographs from Europe and the USA.[15] Its testing and implementation were facilitated by an AI orchestration platform, CARPL.ai (CARPL.ai, San Francisco, CA, USA).[16]Figures 1 and 2 illustrate the typical output data by RBfracture. RBfracture was tested and validated for the detection of fractures in appendicular and pelvic radiographs, without prior prostheses, of patients aged 21 years and above. Radiographs beyond this validated population were excluded from our study radiograph set.
Results:
Ninety-two examinations were included in the final study radiograph set. The AI solution had a sensitivity of 98.9%, an accuracy of 85.9% and an almost perfect agreement with the reference standard.
Conclusion:
An AI fracture detection solution has similar sensitivity to human radiologists in the detection of fractures on ED appendicular and pelvic radiographs. Its implementation offers significant potential measurable cost, manpower and time savings.
Open access
This research is open access.
