AI interprets radiology reports at 91% accuracy
According to a recent article from Clinical Innovation and Technology, researchers from New York's Icahn School of Medicine at Mount Sinai have developed machine learning technology capable of interpreting radiologist reports with an accuracy rate of 91 percent. The original research was published in Radiology.
According to CIT, reserachers trained artificial intelligence (AI) to interpret x-ray, computed tomography (CT) and MRI reports through a set of algorithms designated to detect certain terminology.
"The ultimate goal is to create algorithms that help doctors accurately diagnose patients," said lead author John Zech, a med student at the Icahn School of Medicine at Mount Sinai. "Deep learning has many potential applications in radiology—triaging to identify studies that require immediate evaluation, flagging abnormal parts of cross-sectional imaging for further review, characterizing masses concerning for malignancy—and those applications will require many labeled training examples."
Roughly 96,300 radiologist CT head scan reports were used to train the AI technology. For more information, read the entire story and original study below:
A recent graduate from Dominican University (IL) with a bachelor’s in journalism, Melissa joined TriMed’s Chicago team in 2017 covering all aspects of health imaging. She’s a fan of singing and playing guitar, elephants, a good cup of tea, and her golden retriever Cooper.