The combined interpretation of AI and healthcare professionals lowered the false negative rate (undetected fractures) on radiographs by 30% and allowed a 12% gain in sensitivity, a 5% gain in specificity per patient, without loss of reading speed, on exams specifically selected for their difficulty.
GLEAMER, a French med-tech company that develops AI-based diagnostic aids for radiology, announces that the results of a clinical study evaluating the performance of BoneView®, its AI solution for fracture detection on radiographs, have been published in the prestigious journal "Radiology".
"To our knowledge, this is the first study that evaluates the performance of AI-assisted reading for radiographic fracture detection over the entire appendicular skeleton and on multicenter data," says Dr. Loïc Duron, radiologist at the Adolphe de Rothschild Foundation Hospital (Paris), and first author of the study.
"With this publication, the international scientific community validates the quality and robustness of the results generated, in a context where several solutions are marketed without published objective results," added Prof. Antoine Feydy, MSK radiologist at Cochin Hospital (Paris).
600 adult patients in whom radiographs were obtained after a recent trauma, at 17 imaging centers, were retrospectively included. Six radiologists and six emergency physicians were asked to detect and localize fractures with and without the help of BoneView®. Sensitivity, specificity, and reading times with and without assistance were compared. On top of a significant gain in sensitivity and specificity, AI assistance reduced the average number of false positives by 42% in patients without fractures and average reading time by 15%. Finally, the stand-alone performance of a newer version of the AI system was superior to that of all unassisted readers, including musculoskeletal radiologists. In conclusion, AI-aid improves the diagnostic performance of all physicians, which will enable better patient care.
GLEAMER's first AI solution BoneView® detects and highlights lesions in radiographic images, thus providing healthcare professionals with a safe, reliable, time-saving, and intuitive diagnostic aid. BoneView® received the CE mark IIA in March 2020 and has to date analyzed nearly 2 million images, in more than 130 sites. BoneView® is available in around 20 countries.
View source version on businesswire.com: https://www.businesswire.com/news/home/20210518005021/en/
+ 33 (6) 64 18 99 59