Haue, Holm et al. use unsupervised clustering to subgroup a large set of ischemic heart disease patients from their pre-existing diseases, covering the entire multimorbidity spectrum. They identify subgroups that have different risk profiles and are characterized by different patterns when looking at patient blood tests and genetic profiles.

A new AI model with contributions from the University of Copenhagen can predict the onset of illness across entire populations. But it also raises ethical questions about data security — and about peo...

Nature - A modified large language model called Delphi-2M analyses a person’s medical records and lifestyle to provide risk estimates for more than 1,000 diseases.