NIH's TrialGPT AI Algorithm Expedites Clinical Trial Matching
Key Insights
The NIH has developed TrialGPT, an AI algorithm that efficiently matches potential volunteers to clinical trials listed on ClinicalTrials.gov.
TrialGPT accurately identifies relevant clinical trials for individuals, explaining how they meet enrollment criteria, potentially improving trial enrollment.
Clinicians using TrialGPT experienced a 40% reduction in patient screening time while maintaining the same level of accuracy in matching patients to trials.
Researchers at the National Institutes of Health (NIH) have unveiled TrialGPT, an artificial intelligence (AI) algorithm designed to accelerate the matching of volunteers to clinical trials listed on ClinicalTrials.gov. The AI tool aims to streamline the process, potentially leading to faster progress in medical research.
The study, published in Nature Communications, highlights TrialGPT's ability to successfully identify relevant clinical trials for eligible individuals. The algorithm provides a clear summary explaining how a person meets the criteria for study enrollment. Researchers suggest that this tool could aid clinicians in navigating the extensive range of clinical trials available to their patients.
How TrialGPT Works
A team from NIH’s National Library of Medicine (NLM) and National Cancer Institute developed TrialGPT using large language models (LLMs). The algorithm processes patient summaries containing relevant medical and demographic information. It then identifies relevant clinical trials from ClinicalTrials.gov, excluding those for which the patient is ineligible. TrialGPT subsequently explains how the person meets the study enrollment criteria, providing clinicians with an annotated list of trials ranked by relevance and eligibility.
Stephen Sherry, PhD, Acting Director of NLM, stated, "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."
Accuracy and Efficiency
To assess TrialGPT's predictive accuracy, researchers compared its results to those of three human clinicians who assessed over 1,000 patient-criterion pairs. TrialGPT achieved nearly the same level of accuracy as the clinicians.
In a pilot user study, clinicians using TrialGPT spent 40% less time screening patients while maintaining the same level of accuracy. This suggests that TrialGPT could free up clinicians' time for tasks requiring human expertise.
Impact on Clinical Research
Finding the right clinical trial for interested participants is often a time-consuming and resource-intensive process, which can slow down medical research. Zhiyong Lu, PhD, NLM Senior Investigator and corresponding author of the study, noted, "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."
The research team has been selected for The Director’s Challenge Innovation Award to further assess the model’s performance and fairness in real-world clinical settings. The researchers anticipate that this work could make clinical trial recruitment more effective and help reduce barriers to participation for populations underrepresented in clinical research.