NIH

New AI tool from NIH streamlines clinical trial enrollment process

November 19, 2024

NIH researchers introduced a new AI algorithm named TrialGPT, designed to expedite the matching of potential volunteers to relevant clinical trials listed on ClinicalTrials.gov. Published in Nature Communications, the study demonstrated that TrialGPT can accurately identify eligible clinical trials for patients and provide clear summaries of how they meet enrollment criteria. This advancement aims to help clinicians navigate the complex landscape of clinical trials, ultimately enhancing enrollment rates and accelerating medical research progress.

The algorithm uses large language models to process patient summaries containing essential medical and demographic information. By efficiently filtering through available trials, TrialGPT generates an annotated list ranked by relevance and eligibility, significantly reducing the time clinicians spend on patient screenings—by up to 40%—while maintaining accuracy comparable to human assessments. This tool streamlines the recruitment process and has the potential to improve access to clinical trials for underrepresented populations, thereby fostering more inclusive research practices.

Source:

NIH. (2024, November 18). NIH-developed AI algorithm matches potential volunteers to clinical trials. https://www.nih.gov/news-events/news-releases/nih-developed-ai-algorithm-matches-potential-volunteers-clinical-trials