NIH's TrialGPT AI Expedites Clinical Trial Matching for Volunteers
核心洞察
The NIH has developed TrialGPT, an AI algorithm that accelerates matching potential volunteers to clinical trials listed on ClinicalTrials.gov.
TrialGPT identifies relevant clinical trials for eligible individuals and explains how they meet enrollment criteria, enhancing clinician efficiency.
A study showed TrialGPT achieves similar accuracy to clinicians, reducing screening time by 40% while maintaining the same level of precision.
Researchers at the National Institutes of Health (NIH) have unveiled TrialGPT, an artificial intelligence (AI) algorithm designed to streamline the matching of volunteers to clinical trials listed on ClinicalTrials.gov. Published in Nature Communications, the study highlights TrialGPT's ability to pinpoint relevant clinical trials for eligible individuals and provide clear explanations of their eligibility, potentially accelerating medical research.
How TrialGPT Works
Developed by researchers from NIH's National Library of Medicine (NLM) and National Cancer Institute, TrialGPT leverages large language models (LLMs) to process patient summaries containing medical and demographic information. The algorithm identifies relevant clinical trials, excludes ineligible ones, and explains how the person meets the study enrollment criteria. The output is an annotated list of clinical trials ranked by relevance and eligibility, which clinicians can use to discuss opportunities with their patients.
"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," said NLM Acting Director, Stephen Sherry, PhD.
Accuracy and Efficiency
In a comparative assessment, TrialGPT's results were compared to those of three human clinicians evaluating over 1,000 patient-criterion pairs. TrialGPT achieved nearly the same level of accuracy as the clinicians. A pilot user study further demonstrated that clinicians using TrialGPT spent 40% less time screening patients while maintaining the same level of accuracy.
Impact on Clinical Trial Enrollment
Finding suitable clinical trials for interested participants is often a time-consuming and resource-intensive process. According to NLM Senior Investigator Zhiyong Lu, PhD, TrialGPT could help clinicians connect their patients to clinical trial opportunities more efficiently, saving time for tasks requiring human expertise.
Future Directions
The research team has been selected for The Director's Challenge Innovation Award to further assess TrialGPT's performance and fairness in real-world clinical settings. The goal is to enhance clinical trial recruitment and reduce barriers to participation for populations underrepresented in clinical research.