Google’s DeepMind AI system IDs 50 eye diseases, explains choices
An artificial intelligence (AI) software designed by Google DeepMind and U.K. physicians identified diseases on optical coherence tomography scans and made the correct referral choice in 94 percent of cases, according to a recent Nature Medicine report.
The AI method reviewed patient scans from Moorfields Eye Hospital in London and performed equal or better than eye specialists who analyzed the same scans. The real achievement, however, was in its ability to demonstrate how it made each decision, according to a recent STAT article.
“Doctors and patients don’t want just a black box answer, they want to know why,” said Ramesh Raskar, an associate professor at the Massachusetts Institute of Technology who studies computational imaging, to STAT. “There is a standard of care, and if the AI technique doesn’t follow that standard of care, people are going to be uncomfortable with it, even if it’s the smartest thing in the world."
Although the system was able to identify 50 different eye diseases after reviewing images, authors of the study maintain it will take years, and human supervision, before the method is used clinically, according to STAT.
Read the entire story below:
Matt joined Chicago’s TriMed team in 2018 covering all areas of health imaging after two years reporting on the hospital field. He holds a bachelor’s in English from UIC, and enjoys a good cup of coffee and an interesting documentary.