UNIVERSITY OF MARYLAND, COLLEGE PARK

TrialGPT, an AI tool developed by NIH researchers, matches patients to clinical trials efficiently, reducing clinician workload. It uses large language models for data-efficient, transparent matching, showing high accuracy in preliminary tests. The tool aims to speed up trial recruitment and treatment advances, with ongoing studies to assess real-world application and address enrollment disparities.

NIH introduces TrialGPT, an AI tool leveraging large language models to efficiently match patients to clinical trials, enhancing enrollment and reducing clinician screening time. Preliminary tests show high accuracy and significant time savings, with ongoing research to assess real-world applications and address enrollment disparities.

NIH researchers developed TrialGPT, an AI algorithm, to efficiently match patients with clinical trials on ClinicalTrials.gov. It processes patient summaries to identify eligible trials, explaining enrollment criteria. TrialGPT matched human clinician accuracy, reducing screening time by 40%, aiming to enhance trial recruitment and reduce participation barriers.

The University of Maryland ranks 18th among U.S. research institutions, with combined research expenditures of $1.4 billion in FY2023, reflecting faculty and student dedication to innovation. UMB, a pre-eminent public research university, received over $638 million in awards in FY2024 and collaborates with over 300 bioscience firms.

NIH researchers developed TrialGPT, an AI framework using large language models to streamline clinical trial matching on ClinicalTrials.gov, achieving nearly the same accuracy as human clinicians. TrialGPT analyzes patient summaries to identify eligible trials, reducing clinician screening time by 40% while maintaining accuracy. The tool relies on OpenAI’s GPT-3.5 and GPT-4 models and will be further assessed for performance and fairness in real-world settings.

NIH introduces TrialGPT, an AI algorithm matching patients to clinical trials on ClinicalTrials.gov, aiming to accelerate research and improve enrollment. Developed by NIH's NLM and NCI, TrialGPT uses LLMs to process patient data, exclude ineligible trials, and rank eligible studies. It achieved near-human accuracy in a benchmarking study and demonstrated potential to save clinicians 40% of screening time.

NIH researchers developed TrialGPT, an AI algorithm that efficiently matches potential volunteers to relevant clinical trials on ClinicalTrials.gov, potentially enhancing clinical trial enrollment and medical research advancements.

NIH researchers developed TrialGPT, an AI algorithm, to efficiently match patients to clinical trials on ClinicalTrials.gov, improving enrollment speed and accuracy. TrialGPT processes patient summaries, identifies eligible trials, and explains criteria, reducing clinician screening time by 40% while maintaining accuracy.

Jonathan Dinman, UMCP professor, named IBBR director effective Nov 1, 2024. IBBR, a research partnership between UMCP, UMB, and NIST, focuses on bioscience and biotechnology. Dinman, a virologist, studies programmed ribosomal frameshifting (PRF) in RNA viruses, aiming to develop potential vaccines.