Large Language Model Analysis of Reporting Quality of Randomized Clinical Trial Articles

Can a zero-shot large-language-model (LLM) framework accurately assess Consolidated Standards for Reporting Trials (CONSORT) reporting in randomized clinical trials (RCTs), and what trends does it uncover?In this systematic review, an LLM performed well on 50 benchmark RCTs and then assessed 21 041 open-access RCTs, published from 1966 to 2024. Overall CONSORT compliance rose from 27% before 1990 to 57% after 2010, yet key methodological items remained poorly reported; compliance varied widely by biomedical discipline (35%-63%).These findings suggest that LLMs could enable scalable, reliable auditing of RCT reporting and highlight persistent gaps that journals and funders should target to improve research transparency and reproducibility.

Corresponding Authors: Nicholas P. Tatonetti, PhD (Nicholas.Tatonetti@cshs.org), and Apoorva Srinivasan, MS (Apoorva.Srinivasan@cshs.org), Department of Computational Biomedicine, Cedars-Sinai Medical Center, 8700 Beverly Blvd, Los Angeles, CA 90069.

Link to the article in your story

We encourage you to link out to this article in your story using the link below. It includes an access token that will give free access to the article for your readers up to one year after publication. (The link will be live after the article publishes and embargo is lifted.)

Please see the article for additional information, including full author list, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

Need more information? Contact us.