EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access

Leveraging AI Large Language Models for Writing Clinical Trial Proposals in Dermatology: Instrument Validation Study

Megan Hauptman, Daniel Copley, Kelly Young, Tran Do, Joseph S Durgin, Albert Yang, Jungsoo Chang, Allison Billi, Mio Nakamura, Trilokraj Tejasvi

JMIR Dermatology · 2026

DOI: 10.2196/76674 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift JMIR Dermatology, 2026. Verfasst von Megan Hauptman und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Dermatology, University of Michigan, 1500 E Medical Center Dr, Ann Arbor, MI, 48105, United States, 1 734-936-4054. Hauptthemen laut MEDLINE: Large Language Models, Dermatology, Clinical Trials as Topic, Research Design. Die Arbeit nennt 11 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Large language models (LLMs) are becoming increasingly popular in clinical trial design but have been underused in research proposal development.

Objective

This study compared the performance of commonly used open access LLMs versus human proposal composition and review.

Methods

A total of 10 LLMs were prompted to write a research proposal. Six physicians and each of the LLMs assessed 11 blinded proposals for capabilities and limitations in accuracy and comprehensiveness.

Results

ChatGPT-o1 and Llama 3.1 were rated the most and least accurate, respectively, by human scorers. LLM scorers rated ChatGPT-o1 and DeepSeek R1 as the most accurate. ChatGPT-o1 and Llama 3.1 were rated as the most and least comprehensive, respectively, by human and LLM scorers. LLMs performed poorly on scoring proposals and, on average, rated proposals 1.9 points higher than humans for both accuracy and comprehensiveness.

Conclusions

Paid versions of ChatGPT remain the highest-quality and most versatile option of the available LLMs. These tools cannot replace expert input but serve as powerful assistants, streamlining the development process and enhancing productivity.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsDermatologyClinical Trials as TopicResearch DesignWritingArtificial IntelligenceHumansGenerative Artificial Intelligence

Stichwörter der Autor:innen

AIartificial intelligenceclinical researchclinical trialsdeep learninglarge language modelmachine learningresearch designresearch proposal

Autor:innen und Institutionen

  • Department of Dermatology, University of Michigan, 1500 E Medical Center Dr, Ann Arbor, MI, 48105, United States, 1 734-936-4054.
  • Anduril, Costa Mesa, CA, United States.

Zitieren

APA

Hauptman, M., Copley, D., Young, K., Do, T., Durgin, J. S., Yang, A., Chang, J., Billi, A., Nakamura, M., & Tejasvi, T. (2026). Leveraging AI Large Language Models for Writing Clinical Trial Proposals in Dermatology: Instrument Validation Study. JMIR Dermatology. https://doi.org/10.2196/76674

Vancouver

Hauptman M, Copley D, Young K, Do T, Durgin JS, Yang A, et al. Leveraging AI Large Language Models for Writing Clinical Trial Proposals in Dermatology: Instrument Validation Study. JMIR Dermatology. 2026. doi:10.2196/76674

BibTeX
@article{Hauptman2026,
  author = {Hauptman, Megan and Copley, Daniel and Young, Kelly and Do, Tran and Durgin, Joseph S and Yang, Albert and Chang, Jungsoo and Billi, Allison and Nakamura, Mio and Tejasvi, Trilokraj},
  title = {Leveraging AI Large Language Models for Writing Clinical Trial Proposals in Dermatology: Instrument Validation Study},
  journal = {JMIR Dermatology},
  year = {2026},
  doi = {10.2196/76674}
}
Kostenlos starten →