Applications of Generative Artificial Intelligence for Real-World Evidence Generation: A Protocol for a Living Scoping Review

<b>Introduction:</b> Generative artificial intelligence (genAI) is rapidly evolving, offering an expanding suite of capabilities that go beyond the traditional focus of artificial intelligence (AI) on prediction and classification. GenAI could create transformative practices to support real-world evidence (RWE) generation for health research by streamlining study design, conduct, analysis and reporting, accelerating insights and improving decision-making. However, there is no published overview available describing the range of genAI applications in RWE generation.<br/><br/><b>Objective:</b> To describe where and how genAI is currently applied across the domains of healthcare research tasks specifically for RWE generation, including study design, conduct, analyses and reporting. Additionally, to map genAI applications by tasks and methods across the product lifecycle continuum, and to identify current and emerging uses as well as gaps and opportunities.<br/><br/><b>Methods: </b>This Living Scoping Review (LSR) will search Embase, MEDLINE and additional sources (e.g. gre y literature). Citations will be screened by one human reviewer and a commercially available screening algorithm. The LSR will include primary and secondary (reviews of) reports describing and/or evaluating the application of any genAI model for RWE generation in healthcare, in English, published since 1 January 2024. Data will be extracted from all studies included in the LSR by one independent reviewer using a piloted template, with 10% quality check by a second reviewer. Descriptive statistics will be used to summarise the applications of genAI per RWE research tasks, and the results of genAI evaluations. Thematic analysis will be used to describe genAI application patterns, trends, gaps and opportunities.<br/><br/><b>Living review update:</b> The review protocol and reports will be updated annually, and findings will be published on a publicly available website (e.g. the International Society for Pharmacoepidemiology). <br/>