{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Lasko TA"],"funding":["U.S. Department of Health & Human Services | NIH | U.S. National Library of Medicine","U.S. Department of Health & Human Services | NIH | National Cancer Institute","U.S. Department of Health & Human Services | NIH | National Institute of Arthritis and Musculoskeletal and Skin Diseases","NCI NIH HHS","NLM NIH HHS","NIAMS NIH HHS"],"pagination":["53"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC10907678"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["7(1)"],"pubmed_abstract":["The rising popularity of artificial intelligence in healthcare is highlighting the problem that a computational model achieving super-human clinical performance at its training sites may perform substantially worse at new sites. In this perspective, we argue that we should typically expect this failure to transport, and we present common sources for it, divided into those under the control of the experimenter and those inherent to the clinical data-generating process. Of the inherent sources we look a little deeper into site-specific clinical practices that can affect the data distribution, and propose a potential solution intended to isolate the imprint of those practices on the data from the patterns of disease cause and effect that are the usual target of probabilistic clinical models."],"journal":["NPJ digital medicine"],"pubmed_title":["Why do probabilistic clinical models fail to transport between sites."],"pmcid":["PMC10907678"],"funding_grant_id":["R01 AR076516","CA253923","LM013807","R21 LM013807","AR076516","R01 CA253923"],"pubmed_authors":["Lasko TA","Strobl EV","Stead WW"],"additional_accession":[]},"is_claimable":false,"name":"Why do probabilistic clinical models fail to transport between sites.","description":"The rising popularity of artificial intelligence in healthcare is highlighting the problem that a computational model achieving super-human clinical performance at its training sites may perform substantially worse at new sites. In this perspective, we argue that we should typically expect this failure to transport, and we present common sources for it, divided into those under the control of the experimenter and those inherent to the clinical data-generating process. Of the inherent sources we look a little deeper into site-specific clinical practices that can affect the data distribution, and propose a potential solution intended to isolate the imprint of those practices on the data from the patterns of disease cause and effect that are the usual target of probabilistic clinical models.","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 Mar","modification":"2026-06-26T03:14:25.809Z","creation":"2025-06-01T12:37:25.021Z"},"accession":"S-EPMC10907678","cross_references":{"pubmed":["38429353"],"doi":["10.1038/s41746-024-01037-4"]}}