AI helps radiologists detect bone fractures

OAK BROOK, Ill. — Artificial intelligence (AI) is an effective tool for fracture detection that has the potential to help clinicians in busy emergency departments, according to a study in Radiology.

Missed or delayed diagnosis of fractures on radiography is a common error with potentially serious implications for the patient. The lack of timely access to expert opinion as the growth in imaging volumes continues to outpace the recruitment of radiologists only compounds the problem.

AI can help solve this problem by assisting radiologists, helping to speed up and improve the diagnosis of fractures.

To learn more about the technology’s potential in the setting of fractures, a team of researchers in England reviewed 42 existing studies comparing diagnostic performance in detecting fractures between AI and clinicians. Of the 42 studies, 37 used X-rays to identify fractures and five used CT.

The researchers found no statistically significant difference between the performance of clinicians and that of the RN. The sensitivity of AI to detect fractures was 91-92%.

“We found that the AI ​​worked with a high degree of precision, comparable to the performance of clinicians,” said study lead author Rachel Kuo, MBBChir., of the Botnar Research Center, Department of Orthopedics, of Rheumatology and Musculoskeletal Sciences in Oxford, England. “Importantly, we found this to be the case when the AI ​​was validated using independent external datasets, suggesting that the results may be generalizable to a larger population.”

The study results point to several promising educational and clinical applications for AI in fracture detection, Dr. Kuo said. This could reduce the rate of early misdiagnosis in difficult emergency circumstances, including cases where patients may sustain multiple fractures. It has potential as an educational tool for beginning clinicians.

“It could also be useful as a ‘second reader’, providing clinicians with either reassurance that they have made the correct diagnosis or prompting them to review imaging before treating patients,” said Dr Kuo. .

Dr Kuo warned that research into AI fracture detection was still at a very early preclinical stage. Only a minority of the studies she and her colleagues reviewed evaluated the performance of AI-assisted clinicians, and there was only one example where an AI was evaluated in a prospective study in a clinical setting.

“It remains important for clinicians to continue to exercise their own judgment,” Dr. Kuo said. “AI is not infallible and is subject to bias and error.”

###

“Artificial intelligence in fracture detection: a systematic review and meta-analysis.” Conrad Harrison, B.Sc., MBBS, MRCS, Terry-Ann Curran, MBBCh collaborated with Dr. Kuo. BAO, MD, Benjamin Jones, BMBCh., BA, Alexander Freethy, B.Sc., MBBS, M.Sc., MRCS, David Cussons, B.Sc., MBBS, Max Stewart, MBBChir., BA, Gary S. Collins, B.Sc., Ph.D., and Dominic Furniss, DM, MA, MBBCh., FRCS (Plast).

Radiology is edited by David A. Bluemke, MD, Ph.D., University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, and owned and published by the Radiological Society of North America, Inc. (https://pubs.rsna.org/journal/radiology)

The RSNA is an association of radiologists, radiation oncologists, medical physicists and related scientists promoting excellence in patient care and healthcare delivery through education, research and technological innovation. The Company is based in Oak Brook, Illinois. (RSNA.org)

For user-friendly information on musculoskeletal imaging, visit RadiologyInfo.org.

Warning: AAAS and EurekAlert! are not responsible for the accuracy of press releases posted on EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.