A team from the University of Illinois Urbana-Champaign is developing an open-source AI tool to enhance reporting in randomized, controlled clinical trials, using the NSF-funded Bridges-2 system. Clinical trials are essential for validating the safety and effectiveness of new treatments, yet issues often arise in how they are documented, making it difficult for researchers to evaluate the rigor of studies. By leveraging natural language processing (NLP), the team aims to identify missing elements in trial reports based on established guidelines like CONSORT and SPIRIT. Initial testing yielded promising F₁ scores, indicating the AI’s efficacy in detecting reporting gaps. The researchers aim to refine their model further by increasing data input and improving training techniques. Their overarching goal is to provide journals and authors with a free AI resource to ensure transparency and accuracy in clinical trial publications, ultimately benefiting patient care and medical research integrity.
Source link
