Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
Rao and Rolston discuss recent challenges to foundational assumptions underlying responsive neurostimulation therapy for drug-resistant epilepsy. An emerging mechanistic model helps explain variability in clinical outcomes and suggests this therapy may have untapped potential for reducing seizures.
Clusmann et al. describe how large language models such as ChatGPT could be used in medical practice, research and education. These models could democratize medical knowledge and facilitate access to healthcare, but there are also potential limitations to be considered.
Rouzine and Rozhnova discuss the potential consequences of vaccination on the antigenic evolution of the SARS-CoV-2 virus. The authors outline the possibility of its acceleration by mass vaccination and considerations for future vaccination strategies.
Thorlund et al. discuss considerations when selecting appropriate endpoints for outpatient COVID-19 clinical trials. Improvements in patient outcomes during the COVID-19 pandemic have necessitated changes to the outcomes being assessed.
Badal et al. outline principles that should be adopted during the development of artificial intelligence-based healthcare tools. These principles expand upon principles proposed by several organizations by emphasizing that AI be developed to improve longstanding health care challenges.
Nekkab, Malinga, Braunack-Mayer et al. discuss how modelling can be incorporated early on in the research and development of malaria tools alongside clinical evidence and expert opinion. In addition, population models can provide estimates of potential effectiveness of novel interventions to inform product criteria and support decision-making.