Researchers at Atlanta-based Emory University developed artificial intelligence that they say improves the prediction of successful heart transplants by 10%.
Historically, physicians grade cardiac biopsies to diagnose acute rejection, however, the interpretations can vary by physician, according to a May 28 report from ABC affiliate WSB-TV. Emory worked with researchers at Cleveland-based Case Western Reserve University and Philadelphia-based University of Pennsylvania to create AI that examines cardiac biopsy images to improve the prediction of rejection.
The study, published Feb. 13 in Circulation: Heart Failure, ran the AI on 2,900 patients' images. The AI was 10% better at predicting the success of transplants and was better at providing signs of rejection.
"What is most interesting is not just that the AI approach was able to better predict transplant rejection compared to pathologic grade, but it used a set of image features that were far more intuitive and explainable compared to opaque, 'black box' AI models that are challenging for clinicians to interpret," senior study author Anant Madabhushi, PhD, a biomedical engineering professor at Emory and Atlanta-based Georgia Institute of Technology, said in the release.