Research
AI helps researchers investigate how thousands of medical studies share code
MIT News · By Bwiza Gihana Deborah | Institute for Medical Engineering & Science ·
The Brief
- MIT News reports an AI-based tool used to analyse how thousands of medical studies share their data and code.
- The underlying concern is that access to a study's data and code shows how patients were selected, how missing values were handled and how results were evaluated.
- The source is a short excerpt; details of the tool's method and findings are not included in the provided text.
Why it matters
Science readers who rely on published medical studies can use this kind of work to judge how transparently and reproducibly research is shared.
Who’s affected
- medical researchers
- researchers interested in research reproducibility and open data
- #medical research
- #open data
- #reproducibility
- #artificial intelligence
- #code sharing
The data and code that underpin a research study can tell us what was actually done, and how. In a medical study, for example, how were patients selected for inclusion? How were missing values handled? How were the results evaluated? Access to a study's data and code help…