Article type
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.
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.