RCT-Check

NLP for RCT transparency checks

Project Title: Computational Methods, Resources, and Tools to Assess Transparency and Rigor of Randomized Clinical Trials Funding: National Institutes of Health/National Library of Medicine (R01LM014079)
Project Period: 2022-2026
Role: PI; Evan Mayo-Wilson, UNC (MPI)

Randomized controlled trials (RCTs) are considered the “gold standard” study design to determine the effectiveness of therapeutic interventions; however, they often suffer from rigor and transparency problems, leading to potential research waste. In this project, we develop a set of natural language processing (NLP) methods to identify information related to rigor and transparency from RCT reports (protocols and results publications). These methods will support tools and resources that assist stakeholders of clinical research in maintaining high reporting standards, synthesizing information on methodological quality, and fostering open science practices. They will contribute to improvements throughout the scientific ecosystem, leading to better patient care and health policy.