This is a page that curates AI-related papers published worldwide. All content here is summarized using Google Gemini and operated on a non-profit basis. Copyright for each paper belongs to the authors and their institutions; please make sure to credit the source when sharing.
David Bann, Ed Lowther, Liam Wright, Yevgeniya Kovalchuk
Outline
This paper discusses how recent advances in artificial intelligence (AI), including generative AI, offer new opportunities to accelerate or automate epidemiological research. Unlike disciplines based on physical experiments, much epidemiological research relies on secondary data analysis and is therefore amenable to the use of AI. However, it remains unclear which specific tasks may benefit from AI interventions, or what barriers exist. Current perceptions of AI capabilities are also mixed. This paper maps the overall picture of epidemiological tasks using existing datasets, from literature review to data access, analysis, writing, and dissemination, and identifies areas where existing AI tools offer efficiency gains. While AI can increase productivity in some areas, such as coding and management tasks, its usefulness is limited by limitations of existing AI models (e.g., hallucinations in literature review) and human systems (e.g., barriers to access to datasets). Examples of AI-generated epidemiological outputs (including fully AI-generated papers) demonstrate that recently developed agent systems can design and execute epidemiological analyses, but the quality varies ( see https://github.com/edlowther/automated-epidemiology ). Epidemiologists have new opportunities to empirically test and benchmark AI systems. Realizing the potential of AI requires a two-way engagement between epidemiologists and engineers.
