{"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/intelligent-word-embeddings-of-free-text","title":"Intelligent Word Embeddings of Free-Text Radiology Reports","arxiv_id":"1711.06968","date":"2017-11-19","proceeding":null,"authors":["Imon Banerjee","Sriraman Madhavan","Roger Eric Goldman","Daniel L. Rubin"],"abstract":"Radiology reports are a rich resource for advancing deep learning\napplications in medicine by leveraging the large volume of data continuously\nbeing updated, integrated, and shared. However, there are significant\nchallenges as well, largely due to the ambiguity and subtlety of natural\nlanguage. We propose a hybrid strategy that combines semantic-dictionary\nmapping and word2vec modeling for creating dense vector embeddings of free-text\nradiology reports. Our method leverages the benefits of both\nsemantic-dictionary mapping as well as unsupervised learning. Using the vector\nrepresentation, we automatically classify the radiology reports into three\nclasses denoting confidence in the diagnosis of intracranial hemorrhage by the\ninterpreting radiologist. We performed experiments with varying hyperparameter\nsettings of the word embeddings and a range of different classifiers. Best\nperformance achieved was a weighted precision of 88% and weighted recall of\n90%. Our work offers the potential to leverage unstructured electronic health\nrecord data by allowing direct analysis of narrative clinical notes.","url_abs":"http://arxiv.org/abs/1711.06968v1","url_pdf":"http://arxiv.org/pdf/1711.06968v1.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":"intelligent-word-embeddings-of-free-text","repo_url":"https://github.com/imonban/RadiologyReportEmbedding","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}