{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["647(8088)"],"submitter":["Shmatko A"],"pubmed_abstract":["Decision-making in healthcare relies on understanding patients' past and current health states to predict and, ultimately, change their future course<sup>1-3</sup>. Artificial intelligence (AI) methods promise to aid this task by learning patterns of disease progression from large corpora of health records<sup>4,5</sup>. However, their potential has not been fully investigated at scale. Here we modify the GPT<sup>6</sup> (generative pretrained transformer) architecture to model the progression and competing nature of human diseases. We train this model, Delphi-2M, on data from 0.4 million UK Biobank participants and validate it using external data from 1.9 million Danish individuals with no change in parameters. Delphi-2M predicts the rates of more than 1,000 diseases, conditional on each "],"journal":["Nature"],"pagination":["248-256"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12589094"],"repository":["biostudies-literature"],"pubmed_title":["Learning the natural history of human disease with generative transformers."],"pmcid":["PMC12589094"],"pubmed_authors":["Brunak S","Gerstung M","Jung AW","Fitzgerald T","Shmatko A","Gaurav K","Birney E","Mortensen LH"],"additional_accession":[]},"is_claimable":false,"name":"Learning the natural history of human disease with generative transformers.","description":"Decision-making in healthcare relies on understanding patients' past and current health states to predict and, ultimately, change their future course<sup>1-3</sup>. Artificial intelligence (AI) methods promise to aid this task by learning patterns of disease progression from large corpora of health records<sup>4,5</sup>. However, their potential has not been fully investigated at scale. Here we modify the GPT<sup>6</sup> (generative pretrained transformer) architecture to model the progression and competing nature of human diseases. We train this model, Delphi-2M, on data from 0.4 million UK Biobank participants and validate it using external data from 1.9 million Danish individuals with no change in parameters. Delphi-2M predicts the rates of more than 1,000 diseases, conditional on each ","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Nov","modification":"2026-06-06T13:58:26.932Z","creation":"2026-05-31T03:10:17.073Z"},"accession":"S-EPMC12589094","cross_references":{"pubmed":["40963019"],"doi":["10.1038/s41586-025-09529-3"]}}