{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/generalizability-of-predictive-models-for","title":"Generalizability of predictive models for intensive care unit patients","arxiv_id":"1812.02275","date":"2018-12-06","proceeding":null,"authors":["Alistair E. W. Johnson","Tom J. Pollard","Tristan Naumann"],"abstract":"A large volume of research has considered the creation of predictive models\nfor clinical data; however, much existing literature reports results using only\na single source of data. In this work, we evaluate the performance of models\ntrained on the publicly-available eICU Collaborative Research Database. We show\nthat cross-validation using many distinct centers provides a reasonable\nestimate of model performance in new centers. We further show that a single\nmodel trained across centers transfers well to distinct hospitals, even\ncompared to a model retrained using hospital-specific data. Our results\nmotivate the use of multi-center datasets for model development and highlight\nthe need for data sharing among hospitals to maximize model performance.","url_abs":"http://arxiv.org/abs/1812.02275v1","url_pdf":"http://arxiv.org/pdf/1812.02275v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"generalizability-of-predictive-models-for","repo_url":"https://github.com/alistairewj/icu-model-transfer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1812.02275","atlas_url":"https://app.syntology.ai/?focus=1812.02275","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}