{"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/natural-language-generation-for-electronic","title":"Natural Language Generation for Electronic Health Records","arxiv_id":"1806.01353","date":"2018-06-01","proceeding":null,"authors":["Scott Lee"],"abstract":"A variety of methods existing for generating synthetic electronic health\nrecords (EHRs), but they are not capable of generating unstructured text, like\nemergency department (ED) chief complaints, history of present illness or\nprogress notes. Here, we use the encoder-decoder model, a deep learning\nalgorithm that features in many contemporary machine translation systems, to\ngenerate synthetic chief complaints from discrete variables in EHRs, like age\ngroup, gender, and discharge diagnosis. After being trained end-to-end on\nauthentic records, the model can generate realistic chief complaint text that\npreserves much of the epidemiological information in the original data. As a\nside effect of the model's optimization goal, these synthetic chief complaints\nare also free of relatively uncommon abbreviation and misspellings, and they\ninclude none of the personally-identifiable information (PII) that was in the\ntraining data, suggesting it may be used to support the de-identification of\ntext in EHRs. When combined with algorithms like generative adversarial\nnetworks (GANs), our model could be used to generate fully-synthetic EHRs,\nfacilitating data sharing between healthcare providers and researchers and\nimproving our ability to develop machine learning methods tailored to the\ninformation in healthcare data.","url_abs":"http://arxiv.org/abs/1806.01353v1","url_pdf":"http://arxiv.org/pdf/1806.01353v1.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":"natural-language-generation-for-electronic","repo_url":"https://github.com/scotthlee/nrc","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"de-identification","task_name":"De-identification"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.01353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.01353"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/scotthlee/nrc","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"6885977179a0e54f","entry":"autoencoder","repo":"scotthlee/nrc","repo_kind":"official","path":"models/unsupervised.py","file_url":"https://github.com/scotthlee/nrc/blob/HEAD/models/unsupervised.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6885977179a0e54f"}},{"code_sha256_prefix":"3ccaa8fdca2e23a3","entry":"cider","repo":"scotthlee/nrc","repo_kind":"official","path":"metrics/text.py","file_url":"https://github.com/scotthlee/nrc/blob/HEAD/metrics/text.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3ccaa8fdca2e23a3"}},{"code_sha256_prefix":"9ef4c8fd992a01b9","entry":"embedding_similarity","repo":"scotthlee/nrc","repo_kind":"official","path":"metrics/text.py","file_url":"https://github.com/scotthlee/nrc/blob/HEAD/metrics/text.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9ef4c8fd992a01b9"}},{"code_sha256_prefix":"fdc61d49aa5915e4","entry":"ngrams","repo":"scotthlee/nrc","repo_kind":"official","path":"metrics/text.py","file_url":"https://github.com/scotthlee/nrc/blob/HEAD/metrics/text.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fdc61d49aa5915e4"}},{"code_sha256_prefix":"5073d7497bb337ef","entry":"threshold","repo":"scotthlee/nrc","repo_kind":"official","path":"ae_training.py","file_url":"https://github.com/scotthlee/nrc/blob/HEAD/ae_training.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5073d7497bb337ef"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}