RAPID: a web-based application for Rapid, efficient, and Accurate automatic generation of submission rePortIng checklists based on large language moDels

Article type
Authors
Bian Z1, Chen F2, Chen Y3, Li Z4, Luo X3, Yang Z1, Zhang L4
1School of Chinese Medicine, Hong Kong Baptist University, Hong Kong SAR, China
2School of Information Science & Engineering, Lanzhou University, Lanzhou, China
3Research Unit of Evidence-Based Evaluation and Guidelines, Chinese Academy of Medical Sciences (2021RU017), School of Basic Medical Sciences, Lanzhou University, Lanzhou, China
4Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China
Abstract
Background
Large language models (LLMs) have the potential to enhance the transparency and integrity of research. However, there is a lack of applications and tools that facilitate this process.

Objectives
To develop RAPID, a web-based application that utilizes LLMs to enable researchers to quickly, efficiently, and accurately use reporting checklists in medical research


Methods
We will develop RAPID as a web-based application powered by LLMs. Initially, we will introduce key reporting guideline documents from the EQUATOR Network such as CONSORT, STROBE, and PRISMA to ChatGPT, Gemini, and LLaMA. Subsequently, we will use these LLMs to assess the compliance of different study types with the respective checklists and provide feedback to the models. Finally, we will create a user-friendly web-based application that guides researchers in writing their manuscripts according to the applicable checklist and verifies compliance with reporting requirements.

Results
Currently, the development of RAPID is in progress, and the results will be presented at the conference.

Conclusions
We hope that RAPID can assist researchers in accelerating manuscript preparation and generating submission reporting checklists with higher accuracy and efficiency, ultimately helping patients to benefit from the latest research findings as early as possible. We also hope RAPID can help journal editors and reviewers quickly review the quality of submissions.