EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

A Generative AI Framework for Pharmacokinetic Clinical Study Report Authoring

John Samuelsson iD, Samuel Blakeman, Ezra Alexander, Srividya Neelakantan, Ravi Shankar Prasad Singh iD, May Garrett iD, Allison Murphy, Jing Zhu iD, Subha Madhavan iD, Sheraz Khan iD

Clinical and Translational Science · 2026-06 · 19 (6)

DOI: 10.1111/cts.70644 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Clinical and Translational Science, online erschienen am 15.06.2026. Verfasst von John Samuelsson und 9 weiteren Autor:innen. Beteiligte Einrichtung: Pfizer Inc., New York City, New York, USA. Hauptthemen laut MEDLINE: Generative Artificial Intelligence, Pharmacokinetics. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Clinical Study Reports (CSRs) constitute the final consolidation of findings from clinical studies and routinely include Pharmacokinetic (PK) results. To assist with PK results authoring, we developed a generative Artificial Intelligence (AI) based method that employs a hierarchical, chained large language model (LLM) framework with in‐context learning to draft PK results directly from study Tables, Listings, and Figures (TLFs), with optional human input. Unlike traditional fine‐tuning approaches, our method does not require large datasets or extensive compute, while producing outputs closely aligned with established CSR structure, tone, and analytical conventions using fewer than a dozen example reports. To assess performance, AI‐generated reports and manually expert‐written CSRs were evaluated in two blinded review sessions by clinical pharmacologists and pharmacometricians, focusing on relative bioavailability (rBA) and drug–drug interaction (DDI) studies. The AI‐generated reports achieved an average reporting quality score of ~90% relative to the manually written CSRs. Together, these results demonstrate a practical, scalable solution for assisting PK report authoring in clinical studies, potentially reducing authoring time while maintaining high‐quality standards.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Generative Artificial IntelligencePharmacokineticsHumansBiological AvailabilityDrug InteractionsLarge Language Models

Stichwörter der Autor:innen

artificial intelligenceautomationclinical study reportgenerative AIpharmacokinetics

Autor:innen und Institutionen

  • Pfizer Inc., New York City, New York, USA.
  • Pfizer Inc., San Diego, California, USA.
  • Pfizer Inc., Groton, Connecticut, USA.

ORCID-Profile: John Samuelsson, Ravi Shankar Prasad Singh, May Garrett, Jing Zhu, Subha Madhavan, Sheraz Khan

Zitieren

APA

Samuelsson, J., Blakeman, S., Alexander, E., Neelakantan, S., Singh, R. S. P., Garrett, M., Murphy, A., Zhu, J., Madhavan, S., & Khan, S. (2026). A Generative AI Framework for Pharmacokinetic Clinical Study Report Authoring. Clinical and Translational Science, 19(6). https://doi.org/10.1111/cts.70644

Vancouver

Samuelsson J, Blakeman S, Alexander E, Neelakantan S, Singh RSP, Garrett M, et al. A Generative AI Framework for Pharmacokinetic Clinical Study Report Authoring. Clinical and Translational Science. 2026;19(6). doi:10.1111/cts.70644

BibTeX
@article{Samuelsson2026,
  author = {Samuelsson, John and Blakeman, Samuel and Alexander, Ezra and Neelakantan, Srividya and Singh, Ravi Shankar Prasad and Garrett, May and Murphy, Allison and Zhu, Jing and Madhavan, Subha and Khan, Sheraz},
  title = {A Generative AI Framework for Pharmacokinetic Clinical Study Report Authoring},
  journal = {Clinical and Translational Science},
  year = {2026},
  volume = {19},
  number = {6},
  doi = {10.1111/cts.70644}
}
Kostenlos starten →