Artificial intelligence may improve detection of fractures by X rays in trauma patients

France: The use of artificial intelligence (AI) software is helpful for radiologists to deliver better performance in detecting bone fractures on x-rays in trauma patients, says a recent study published in Diagnostic and Interventional Imaging. 

The study found that AI-assisted radiologists work faster and better than unassisted radiologists. AI could be of great help to radiologists in daily trauma emergencies and could decrease the cost of missed fractures. 

The study was conducted by Lisa Canoni-Meynet, Department of Radiology, CHU de Besancon, Besançon, France, and colleagues with the objective to compare the performance of radiologists with and without AI assistance for detecting bone fractures from trauma emergencies. 

For this purpose, the researchers retrospectively included five hundred consecutive patients (232 women, 268 men) with a mean age of 37 years. Three radiologists independently interpreted radiographs without then with AI assistance after a 1-month minimum washout period. Consensus reading between musculoskeletal radiologists and AI results was used to determine the ground truth. 

A comparison was made between patient-wise sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for fracture detection and reading time of unassisted and AI-assisted readings of radiologists. Their performances were also assessed by receiver operating characteristic (ROC) curves.