When put to the test by a pair of neurologists at the Hadassah Medical Organization, AI chatbots like ChatGPT and Google’s Gemini exhibited cognitive limitations similar to those seen in human cognitive decline, according to a new study published in the peer-reviewed medical journal The BMJ, Newsweek reports.
The study’s authors hope the results spark conversations about the differences between AI and human doctors — and the important roles that both can play, Hadassah senior neurologist Dr. Roy Dayan told Newsweek.
“The current debate centers on whether language models can replace doctors. It wouldn’t surprise me if, soon, healthcare providers use them as an initial screening tool,” Dr. Dayan told Ynet News. “However, much of medical interaction goes beyond recalling facts; it involves visual abstraction and interpretation, and we’re not there yet.”
In addition to Dr. Dayan, Hadassah senior neurologist Dr. Benjamin Oliel worked with data scientist Gal Kopelvitz on the study.
Read the full story in Newsweek.
Read the full story at Ynet News.
Read More
AI, IT and Nanotechnology: Today’s Healing Odyssey
Hadassah AI Model a Breakthrough in Personalized Cancer Care