EpidemiologicalAlchemy in the AI era comes under close scrutiny-but is it entirely without meaning?"drawing attention to an emerging concern in contemporary epidemiological research. 1The letter highlights a phenomenon in which technically correct but conceptually weak studies are rapidly produced by combining open datasets with generative artificial intelligence (AI).While the data and tools themselves are legitimate, their uncritical use can undermine the scientific value of epidemiological research.Open science has long been promoted for its ability to enhance transparency, reproducibility, and equity in research. 2Large-scale datasets, such as the United States National Health and Nutrition Examination Survey (NHANES) 3 and the Global Burden of Disease (GBD) 4 study, have enabled researchers worldwide to explore important population health questions without the barriers of primary data collection.However, the rapid development of generative AI has introduced new challenges to this ecosystem.
Katanoda et al. (2026) studied this question.