Stanford Center for Digital Health

@stanfordcdh.bsky.social

Shaping the future of digital health, together.

In a study, CDH Affiliated Faculty Jonathan Chen & co-authors, found that LLMs outperformed both physicians & older AI systems on sophisticated clinical reasoning cases — surpassing a benchmark that has defined expert medical computing for 65+ years. Read more: www.science.org/doi/10.1126/...

Performance of a large language model on the reasoning tasks of a physician

More than 65 years ago, complex clinical diagnostic reasoning cases were introduced as the gold standard for the evaluation of expert medical computing systems, a standard that has held ever since. In...

science.org