{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Lu MY"],"funding":["NHGRI NIH HHS","NIGMS NIH HHS"],"pagination":["466-473"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11464372"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["634(8033)"],"pubmed_abstract":["Computational pathology<sup>1,2</sup> has witnessed considerable progress in the development of both task-specific predictive models and task-agnostic self-supervised vision encoders<sup>3,4</sup>. However, despite the explosive growth of generative artificial intelligence (AI), there have been few studies on building general-purpose multimodal AI assistants and copilots<sup>5</sup> tailored to pathology. Here we present PathChat, a vision-language generalist AI assistant for human pathology. We built PathChat by adapting a foundational vision encoder for pathology, combining it with a pretrained large language model and fine-tuning the whole system on over 456,000 diverse visual-language instructions consisting of 999,202 question and answer turns. We compare PathChat with several multimo"],"journal":["Nature"],"pubmed_title":["A multimodal generative AI copilot for human pathology."],"pmcid":["PMC11464372"],"funding_grant_id":["R35 GM149270","T32 HG002295"],"pubmed_authors":["Patel A","Kim A","Lu MY","Gerber G","Pouli D","Soliman A","Chen C","Weishaupt LL","Chen B","Mahmood F","Chen RJ","Chow AK","Zhao M","Williamson DFK","Ding T","Liang I","Le LP","Ikemura K","Wang JJ","Parwani AV"],"additional_accession":[]},"is_claimable":false,"name":"A multimodal generative AI copilot for human pathology.","description":"Computational pathology<sup>1,2</sup> has witnessed considerable progress in the development of both task-specific predictive models and task-agnostic self-supervised vision encoders<sup>3,4</sup>. However, despite the explosive growth of generative artificial intelligence (AI), there have been few studies on building general-purpose multimodal AI assistants and copilots<sup>5</sup> tailored to pathology. Here we present PathChat, a vision-language generalist AI assistant for human pathology. We built PathChat by adapting a foundational vision encoder for pathology, combining it with a pretrained large language model and fine-tuning the whole system on over 456,000 diverse visual-language instructions consisting of 999,202 question and answer turns. We compare PathChat with several multimo","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 Oct","modification":"2026-07-14T20:37:28.879Z","creation":"2025-04-06T03:48:06.068Z"},"accession":"S-EPMC11464372","cross_references":{"pubmed":["38866050"],"doi":["10.1038/s41586-024-07618-3"]}}