Bacterial infection is a key cause of mortality in patients with acute-on-chronic liver failure (ACLF). In this study, we aimed to identify metabolite biomarkers and develop a novel machine learning model for early identification of bacterial infection in ACLF.

When a glass of red wine arrives at the table, most drinkers make a snap judgment before taking a sip. Is the color deep enough? Does the hue suggest quality, or raise a red flag? For years, that visual scrutiny has posed a challenge to an emerging category of wine grapes. Interspecific hybrid varieties – cultivars bred by crossing multiple Vitis vinifera species to withstand disease, cold and the mounting pressures of climate change – have been viewed with skepticism by winemakers and sommeliers who worried that the wines they produce simply don't look the part.

A versatile transistor enables AI hardware to filter image data before analysis and adapt to different tasks, reducing energy consumption with little loss of accuracy.

AI-assisted TB screening could reduce costs and bring diagnostic support to underserved communities, helping narrow gaps in public healthcare in the Philippines.

Researchers from the Japan Advanced Institute of Science and Technology, Japan, assessed the ethics of large language model-generated advice for modifying built environments to support health. In the first study of its kind, researchers evaluated 180 ChatGPT responses across six health pathways, neighborhood income contexts, and budget conditions using four ethical criteria. ChatGPT consistently avoided harmful recommendations and rarely gave lower-income neighborhoods weaker proposals, but showed less consistent community participation and oversight, particularly under constraints.