The National Institutes of Health (NIH) has unveiled a new artificial intelligence (AI) algorithm designed to more efficiently match potential clinical trial participants to appropriate studies.
Known as TrialGPT, the NIH algorithm analyzes patient data to identify relevant clinical trials listed on ClinicalTrials.gov. It offers a potentially transformative tool for accelerating medical research and improving trial enrollment.
A study published in Nature Communications highlights TrialGPT’s ability to accurately assess eligibility criteria and generate clear summaries for clinicians, enabling faster and more informed decision-making. Developed by NIH’s National Library of Medicine (NLM) and National Cancer Institute researchers, TrialGPT uses large language models (LLMs) to process patient summaries, exclude ineligible trials and rank eligible studies by relevance.
“Machine learning and AI technology have held promise in matching patients with clinical trials, but their practical application across diverse populations still needed exploration,” said NLM Acting Director Stephen Sherry. “This study shows we can responsibly leverage AI technology so physicians can connect their patients to a relevant clinical trial that may be of interest to them with even more speed and efficiency.”
Benchmarking and addressing barriers to clinical research
To evaluate its accuracy, the research team compared TrialGPT’s results against assessments from human clinicians for more than 1,000 patient-criterion pairs. The algorithm achieved nearly the same level of accuracy as the clinicians.
In a pilot user study, TrialGPT also demonstrated its potential to save time. Clinicians using the algorithm spent 40% less time screening patient eligibility while maintaining the same accuracy as manual methods. This efficiency could allow healthcare providers to focus more on complex tasks that require human expertise.
Clinical trials play a critical role in advancing medical discoveries, yet identifying eligible participants is often a labor-intensive process that delays progress. TrialGPT aims to reduce these barriers, potentially increasing access to trials for underrepresented populations and improving overall recruitment effectiveness.
“Our study shows that TrialGPT could help clinicians connect their patients to clinical trial opportunities more efficiently and save precious time that can be better spent on harder tasks that require human expertise,” said NLM Senior Investigator and corresponding author of the study, Zhiyong Lu.
Future developments
Given its promising results, the TrialGPT research team has been awarded The Director’s Challenge Innovation Award to evaluate the model’s real-world performance and ensure its fairness across diverse populations.
The study was conducted in collaboration with researchers from Albert Einstein College of Medicine, the University of Pittsburgh, the University of Illinois Urbana-Champaign, and the University of Maryland, College Park.
For more information about NLM and its initiatives, visit NLM’s website.
