Media report · AI-ASSISTED BRIEF
MIT-Led Study Uses LLMs to Audit Code Sharing Across Nearly 4,000 Medical Studies
Report publication · YYSI publication
According to MIT News, An MIT and Dana-Farber-led team used large language models to screen nearly 4,000 clinical prediction studies and hundreds of linked code repositories, finding that only about one in eight studies reported sharing code and that public code often lacked documentation needed for reuse. Published in Nature Medicine, the findings are informing TRIPOD-Code, a reporting guideline for what researchers should share.
Source & context
news.mit.edu · Read the original source ↗
This AI-assisted brief attributes information to the linked media report. It is not an official announcement or independent YYSI reporting. Consult the original report and its evidence.