EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Translating evidence into practice: adapting TrialGPT for real-world clinical trial eligibility screening

Mahanazuddin Syed iD, Muayad Hamidi, Manju Bikkanuri, Nicole Adele Dierschke, Haritha Vardhini Katragadda, Meredith Zozus iD, Antonio Lucio Teixeira

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.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

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)

Electronic Health RecordsPatient SelectionClinical Trials as TopicEligibility DeterminationNatural Language ProcessingHumansSensitivity and Specificity

Stichwörter der Autor:innen

artificial intelligenceclinical trial eligibilityelectronic health recordspatient screening

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}
}
Kostenlos starten →