Back to news

AI · Article

AI Review Finds Medical Studies Often Share Code Without Enough Detail to Reuse

MIT News ·

At a glance

MIT and Dana-Farber researchers used large language models to review nearly 4,000 clinical prediction studies and the code they linked to. They found code sharing is still uncommon, and that posting code publicly does not always come with the documentation needed to reuse it.

Key points

Why it matters

Doctors and patients may rely on these prediction models for care decisions, so others need to be able to check how they were built and tested.

Original source

AI helps researchers investigate how thousands of medical studies share code

MIT News · Nov 20, 07:15 KST

Read on MIT News ↗

AI summarized the original article. Check the original for accuracy. Copyright belongs to MIT News.

AI