AI assistance helped reduce undetected fractures by 29 percent and increased reader sensitivity by 16 percent.
Missed fractures are a common cause of diagnostic discrepancy between the initial radiographic interpretation and the final reading by radiologists. Faced with this situation, a group of researchers from the Boston University School of Medicine has carried out a study in which the artificial intelligence (IA) can help doctors find fractures on X-rays.
“Our AI algorithm can quickly and automatically detect X-rays positive for fractures and mark those studies in the system so that radiologists can prioritize their reading, “he explained Ali Guermaiz, Chief of Radiology at the ‘VA Boston Healthcare System’ and Professor of Radiology and Medicine at the Boston University School of Medicine (BUSM).
In this sense, Guermaiz underlines in the study that “the system also highlights the regions of interest with bounding boxes around the areas where fractures are suspected. This can potentially contribute to reduce waiting time when visiting the hospital or clinic before patients can get a positive fracture diagnosis. ”
To do this, the researchers used a wide variety of readers, including radiologists, orthopedic surgeons, emergency physicians, physician assistants, rheumatologists, and family physicians, to simulate real-life scenarios. “The diagnostic accuracy of each reader’s fractures, with and without the help of AI, was compared to the ‘gold standard.’ We also evaluated the diagnostic performance of AI alone compared to that benchmark test. “
|
“Artificial intelligence assistance helped reduce undetected fractures by 29%” |
“The assistance of AI helped reduce undetected fractures by 29 percent and it increased reader sensitivity by 16 percent, and by 30 percent for exams with more than one fracture, while improving specificity by 5 percent, “Guermaiz notes in the study.
In addition, the principal investigator notes that “AI can be a powerful tool to help radiologists and other clinicians improve diagnostic performance and increase efficiency. In addition, the technology has the potential to improve the patient experience in the hospital. or the clinic. ”
Artificial intelligence applied to other diseases or disorders
This technology has applications beyond those mentioned. Guermaiz assures that “our study focused on the diagnosis of fractures, but a similar concept can be applied to other diseases and disorders“In this sense, he highlights that the interest of his research” is to know what is the best way to use AI to help improve patient care, instead of making artificial intelligence replace health care. ”
Although it may contain statements, data or notes from health institutions or professionals, the information contained in Medical Writing is edited and prepared by journalists. We recommend that the reader be consulted with any health-related question with a healthcare professional.