{"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/multi-layer-representation-learning-for","title":"Multi-layer Representation Learning for Medical Concepts","arxiv_id":"1602.05568","date":"2016-02-17","proceeding":null,"authors":["Edward Choi","Mohammad Taha Bahadori","Elizabeth Searles","Catherine Coffey","Jimeng Sun"],"abstract":"Learning efficient representations for concepts has been proven to be an\nimportant basis for many applications such as machine translation or document\nclassification. Proper representations of medical concepts such as diagnosis,\nmedication, procedure codes and visits will have broad applications in\nhealthcare analytics. However, in Electronic Health Records (EHR) the visit\nsequences of patients include multiple concepts (diagnosis, procedure, and\nmedication codes) per visit. This structure provides two types of relational\ninformation, namely sequential order of visits and co-occurrence of the codes\nwithin each visit. In this work, we propose Med2Vec, which not only learns\ndistributed representations for both medical codes and visits from a large EHR\ndataset with over 3 million visits, but also allows us to interpret the learned\nrepresentations confirmed positively by clinical experts. In the experiments,\nMed2Vec displays significant improvement in key medical applications compared\nto popular baselines such as Skip-gram, GloVe and stacked autoencoder, while\nproviding clinically meaningful interpretation.","url_abs":"http://arxiv.org/abs/1602.05568v1","url_pdf":"http://arxiv.org/pdf/1602.05568v1.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":"multi-layer-representation-learning-for","repo_url":"https://github.com/mp2893/med2vec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"multi-layer-representation-learning-for","repo_url":"https://github.com/ranjanisubramanyan/Patient-data-representation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"document-classification","task_name":"Document Classification"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"medical-diagnosis","task_name":"Medical Diagnosis"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"glove","method_name":"GloVe"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1602.05568","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}