iCreatAI News
Skip to content
Trending storyUpdating

MIT team uses LLM to review code sharing in nearly 4,000 medical papers

1 reports1 sources14 hr agoUpdated

Understand this story

AI overview

A team from MIT and the Dana-Farber Cancer Institute used a large language model to screen nearly 4,000 clinical prediction model studies and found that only about one-eighth reported sharing code. The study was published in Nature Medicine, and the results are being used to develop the reporting standard TRIPOD-Code. The study also found that public code does not necessarily mean reusable documentation and supporting information are available; the proportion of code sharing varied across journals from zero to more than 70%, and sharing rates remained low at some journals that have sharing policies.

AI overview based on source reports · Updated 12 hr ago

Coverage timeline

Follow the coverage to explore different perspectives.

Nov 20
  1. MIT News AI
    AI helps researchers investigate how thousands of medical studies share code

    An international team led by MIT and Dana-Farber Cancer Institute researchers used large language models to examine nearly 4,000 clinical prediction studies, identifying statements about shared code and assessing hundreds of linked repositories. The review, published in Nature Medicine, found that only about 1 in 8 studies reported sharing code, and that making code public does not consistently mean providing the documentation and supporting information needed for reuse. The findings are informing TRIPOD-Code, a reporting guideline being developed to clarify what researchers should share.

Activity for this story

Current comparable activity
7
Peak comparable activity
10Nov 20 08:00
Change in the past 24 hours
–

Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.