Abstract

With the rapid advancement of artificial intelligence (AI), large language models (LLMs) such as ChatGPT have shown promising potential for transforming healthcare research and practice. This study explores using LLM agents in conducting a meta-analysis of medical journal articles and identifying trends in ChatGPT applications within the medical field. By leveraging LLMs and agentic Retrieval-Augmented Generation (RAG) technology, a proof-of-concept (POC) report was generated from recent medical journal articles. The study summarizes current trends in ChatGPT applications in healthcare, aims to (1) leverage LLM agents to generate a POC report after reading the newest medical articles, and (2) examine the collaborative and interpretative capacities of LLM agents. The findings reveal that LLMs can efficiently extract and synthesize basic and contextual information from numerous documents, addressing the growing challenge of timely evidence synthesis in medicine. Trend analysis via LLMs enables broader and deeper insights than traditional human reviews, facilitating knowledge discovery, minimizing human bias, and enhancing resource allocation and policy decisions. While challenges such as interpretability, data limitations, and clinical relevance remain, the study underscores the developmental potential of LLM tools for medical literature review and their role in advancing healthcare research, education, and practice.

Download

Share

COinS