Plain Language Summary

What is it about? The study introduces the ELEVATE-GenAI framework, which provides guidelines for reporting the use of large language models, a form of artificial intelligence, in health economics and outcomes research. This is important because these models can significantly improve how health data is analyzed, but there is a lack of standardized reporting practices. The researchers aimed to address this problem by creating a framework that ensures transparency, accuracy, and reproducibility in studies using these models. This framework fills a gap in existing knowledge by offering specific guidelines for health economics research. The paper proposes a checklist that researchers can use to report their findings more effectively, thereby contributing to a better understanding of how to integrate large language models into health research.

How was the research conducted? The study is based on a literature review and expert input to develop the framework. This methodological approach involved reviewing existing guidelines and frameworks related to artificial intelligence and health research to identify gaps and areas for improvement. The researchers applied this framework to 2 case studies in health economics, one involving systematic literature reviews and the other involving economic modeling. The method used was primarily a combination of literature review and practical application to real-world cases. The objects of study were the processes and outcomes of using large language models in health research. This method was chosen to ensure that the framework is both comprehensive and applicable to different research contexts.

What were the results? The main finding is that the ELEVATE-GenAI framework provides a structured way to report studies using large language models in health economics, which can improve transparency and reproducibility. Additional findings showed that the framework is applicable to various research contexts, as demonstrated by its successful application to the 2 case studies.

Why are the results important? For health technology assessment agencies, these results underline the importance of having clear guidelines to assess the integration of artificial intelligence in research. Practically, the findings could lead to improved research practices and more reliable health data analysis. The primary beneficiaries are researchers and healthcare decision makers who will have access to more robust and reproducible studies.

What are the strengths and weaknesses of this study? The study’s main strength is its comprehensive approach to developing a framework tailored to health economics and outcomes research. However, a limitation is that the framework needs further empirical testing to validate its effectiveness across different research scenarios. Future research could focus on applying the framework to a broader range of studies and refining it based on community feedback and advances in artificial intelligence.

^{Note: This content was created with assistance from artificial intelligence (AI) and has been reviewed and edited by ISPOR staff. For more information or for inquiries on ISPOR’s AI policy, click here or contact us at info@ispor.org.}