TrialGPT

Latest News

Our TrialGPT Paper is Highlighted by Nature Communications

Nature Communications chose to feature our article in their dedicated Editors' Highlights of recent published research on "AI and machine learning".

NIH-developed AI Algorithm Matches Potential Volunteers to Clinical Trials

Researchers from the National Institutes of Health (NIH) have developed an AI algorithm to speed up matching potential volunteers to relevant clinical research trials.

Dr. Zhiyong Lu Received 2024 NLM Regents Award

Dr. Zhiyong Lu was honored at the 2024 NLM Regents meeting for his leadership in developing TrialGPT.

TrialGPT 2.0 Selected for NIH Director's Challenge Innovation Awards

We have developed a proof-of-concept system named TrialGPT that utilizes LLMs to efficiently match patients with suitable clinical trials.

Highlights

An end-to-end framework for zero-shot patient-to-trial matching with LLM
Comprises three modules: TrialGPT-Retrieval, TrialGPT-Matching, and TrialGPT-Ranking
Achieves an accuracy of 87.3% with faithful explanations, close to the expert performance
Reduces the screening time by 42.6% in patient recruitment

Learn more

Cite TrialGPT

Nature Communications

2024

Matching Patients to Clinical Trials with Large Language Models

Qiao Jin, Zifeng Wang, Charalampos S. Floudas, Fangyuan Chen, Changlin Gong, Dara Bracken-Clarke, Elisabetta Xue, Yifan Yang, Jimeng Sun, Zhiyong Lu

Contacts

Qiao Jin, MD
Research Fellow
Division of Intramural Research, NLM, NIH
Zhiyong Lu, PhD FACMI FIAHSI
Senior Investigator
Division of Intramural Research, NLM, NIH

An AI Powered Tool for Matching Patients to Clinical Trials