Leveraging Artificial Intelligence Large Language Models for Writing Clinical Trial Proposals in Dermatology (Preprint)
Preprint
- 28 August 2025
- preprint
- Published by JMIR Publications Inc. in JMIR Preprints
Abstract
BACKGROUND Large language models (LLMs) are becoming increasingly popular in clinical trial design but have been underutilized in research proposal development. OBJECTIVE This study compares the performance of commonly used open access LLMs versus human proposal composition and review. METHODS Ten 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 Chat GPT o1 was rated the most accurate and LLaMA 3.1 the least accurate by human scorers. LLM scorers rated Chat GPT o1 and Deepseek R1 the most accurate. Chat GPT o1 was the most comprehensive and LLaMA 3.1 the least comprehensive 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 available LLMs. These tools cannot replace expert input but serve as powerful assistants, streamlining the development process and enhancing productivity. CLINICALTRIAL n/aKeywords
This publication has 9 references indexed in Scilit:
- Who Knows Anatomy Best? A Comparative Study of ChatGPT ‐4o, DeepSeek , Gemini, and ClaudeClinical Anatomy, 2025
- From RAGs to riches: Utilizing large language models to write documents for clinical trialsClinical Trials, 2025
- Enhancing Human-Robot Interaction through Advanced Natural Language Processing TechniquesInternational Journal of Scientific Research in Engineering and Management, 2024
- Artificial intelligence in dermatology: advancements and challenges in skin of colorInternational Journal of Dermatology, 2024
- Artificial Intelligence Applied to clinical trials: opportunities and challengesHealth and Technology, 2023
- Artificial intelligence in healthcare: transforming the practice of medicineFuture Healthcare Journal, 2021
- Artificial Intelligence for Clinical Trial DesignTrends in Pharmacological Sciences, 2019
- To Apply or Not to Apply: A Survey Analysis of Grant Writing Costs and BenefitsPLOS ONE, 2015
- On the time spent preparing grant proposals: an observational study of Australian researchersBMJ Open, 2013