Translating evidence into practice: adapting TrialGPT for real-world clinical trial eligibility screening
Journal of the American Medical Informatics Association · 01.04.2026 · 33 (4) · 909-913
DOI: 10.1093/jamia/ocag006 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, online erschienen am 04.02.2026. Verfasst von Mahanazuddin Syed und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Population Health Sciences, University of Texas Health Science Center at San Antonio, San Antonio, TX 78229, United States. Hauptthemen laut MEDLINE: Electronic Health Records, Patient Selection, Clinical Trials as Topic, Eligibility Determination. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCATS NIH HHS, NIA NIH HHS, NIH.
Abstract (Originalsprache)
Objectives
To evaluate the performance of a locally deployed adaptation of TrialGPT, a large language model (LLM) system for identifying trial-eligible patients from unstructured electronic health record (EHR) data. Materials and Methods TrialGPT was re-engineered for secure, deployment at UT Health San Antonio using a locally hosted LLM. It was optimized for real-world data needs through a longitudinal patient–encounter–note hierarchy mirroring EHR documentation. Performance was evaluated in two stages: (1) benchmarking against an expert-adjudicated gold corpus (n = 149) and (2) comparative validation against manual screening (n = 55).
Results
Against the expert-adjudicated corpus, the system achieved 81.8% sensitivity, 97.8% specificity, and a positive predictive value of 75.0%. Compared with manual screening, it identified more than twice as many truly eligible patients (81.8% vs 36.4%) while preserving equivalent specificity.
Conclusion
The adapted TrialGPT framework operationalizes trial matching, translating EHR data into actionable screening intelligence for efficient, scalable clinical trial recruitment.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Population Health Sciences, University of Texas Health Science Center at San Antonio, San Antonio, TX 78229, United States.
- Glenn Biggs Institute for Alzheimer's & Neurodegenerative Diseases, University of Texas Health Science Center at San Antonio, San Antonio, TX 78229, United States.
ORCID-Profile: Mahanazuddin Syed, Meredith Zozus
Förderung
- NCATS NIH HHS
- NIA NIH HHS
- NIH
- National Center for Advancing Translational Sciences
- National Institute on Aging
Zitieren
APA
Syed, M., Hamidi, M., Bikkanuri, M., Dierschke, N. A., Katragadda, H. V., Zozus, M., & Teixeira, A. L. (2026). Translating evidence into practice: adapting TrialGPT for real-world clinical trial eligibility screening. Journal of the American Medical Informatics Association, 33(4), 909-913. https://doi.org/10.1093/jamia/ocag006
Vancouver
Syed M, Hamidi M, Bikkanuri M, Dierschke NA, Katragadda HV, Zozus M, et al. Translating evidence into practice: adapting TrialGPT for real-world clinical trial eligibility screening. Journal of the American Medical Informatics Association. 2026;33(4):909-913. doi:10.1093/jamia/ocag006
BibTeX
@article{Syed2026,
author = {Syed, Mahanazuddin and Hamidi, Muayad and Bikkanuri, Manju and Dierschke, Nicole Adele and Katragadda, Haritha Vardhini and Zozus, Meredith and Teixeira, Antonio Lucio},
title = {Translating evidence into practice: adapting TrialGPT for real-world clinical trial eligibility screening},
journal = {Journal of the American Medical Informatics Association},
year = {2026},
volume = {33},
number = {4},
pages = {909--913},
doi = {10.1093/jamia/ocag006}
}
EUVIMED