The model incorporates specific data from MRI exams with patient risk factors to predict whether a person is likely to develop clinically significant prostate cancer.
Finely tuned, pre-trained large language models are beginning to reliably translate image content into text, but are they ready to take on medical images?
Researchers tracked data from more than 400,000 patients for a new meta-analysis, presenting their findings in the Journal of the American Heart Association.
"I wasn’t expecting these results among women in this lower age group, because we usually see increased risk for heart disease among older women," one cardiologist said. "It was definitely surprising.”