Biomedical AI research, evaluation methods, benchmarks, validation, safety, source policy, and editorial methodology.
This study aims to evaluate the value of AI-derived CCTA parameters in predicting cardiovascular events in CAD patients using ICA and QFR as reference standards and investigating associations with MACE during follow-up and modifying factors such as lipid-lowering therapies and inflammatory biomarkers.
Open original
DialysisBot is a multiplatform AI chatbot designed to support hemodialysis patients in self-management of their disease.
Open original
Trust in clinical AI must be earned through prospective studies in real-world settings.
Open original
Source: Nature Medicine, Published online: 13 September 2026; doi:10.1038/s41591-026-04488-2
Open original
Nature Biotechnology, Published online: 10 September 2026; doi:10.1038/s41587-026-03311-0 AI-guided design of complete bacteriophage genomes
Open original
Transfer learning from European cohorts improves prediction in small underrepresented populations but degrades accuracy in larger cohorts.
Open original
GigaPath-Flash and GigaTIME-Flash: Toward population-scale discovery with efficient pathology foundation models, according to Microsoft Research AI.
Open original
Nature Biotechnology, Published online: 31 August 2026; doi:10.1038/s41587-026-03213-1 Symbiotic relationships of microorganisms are predicted and cataloged with a machine learning tool.
Open original