{"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/language-models-are-an-effective-patient","title":"Language Models Are An Effective Patient Representation Learning Technique For Electronic Health Record Data","arxiv_id":"2001.05295","date":"2020-01-06","proceeding":null,"authors":["Ethan Steinberg","Ken Jung","Jason A. Fries","Conor K. Corbin","Stephen R. Pfohl","Nigam H. Shah"],"abstract":"Widespread adoption of electronic health records (EHRs) has fueled the development of using machine learning to build prediction models for various clinical outcomes. This process is often constrained by having a relatively small number of patient records for training the model. We demonstrate that using patient representation schemes inspired from techniques in natural language processing can increase the accuracy of clinical prediction models by transferring information learned from the entire patient population to the task of training a specific model, where only a subset of the population is relevant. Such patient representation schemes enable a 3.5% mean improvement in AUROC on five prediction tasks compared to standard baselines, with the average improvement rising to 19% when only a small number of patient records are available for training the clinical prediction model.","url_abs":"https://arxiv.org/abs/2001.05295v2","url_pdf":"https://arxiv.org/pdf/2001.05295v2.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":"language-models-are-an-effective-patient","repo_url":"https://github.com/som-shahlab/ehr_ml","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"language-models-are-an-effective-patient","repo_url":"https://github.com/som-shahlab/femr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2001.05295","atlas_url":"https://app.syntology.ai/?focus=2001.05295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.05295"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/som-shahlab/ehr_ml","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/som-shahlab/femr","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5},"by_repo_kind":{"listed":{"samples":5,"ran":5,"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":"ca925e93c3ecd2d6","entry":"get_subsequent_mask","repo":"som-shahlab/ehr_ml","repo_kind":"listed","path":"ehr_ml/clmbr/rnn_model.py","file_url":"https://github.com/som-shahlab/ehr_ml/blob/HEAD/ehr_ml/clmbr/rnn_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca925e93c3ecd2d6"}},{"code_sha256_prefix":"c1d613c7acd1cde0","entry":"hash_rand_rang","repo":"som-shahlab/ehr_ml","repo_kind":"listed","path":"ehr_ml/labeler.py","file_url":"https://github.com/som-shahlab/ehr_ml/blob/HEAD/ehr_ml/labeler.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c1d613c7acd1cde0"}},{"code_sha256_prefix":"47717bef92027d49","entry":"read_patient_split","repo":"som-shahlab/ehr_ml","repo_kind":"listed","path":"ehr_ml/splits.py","file_url":"https://github.com/som-shahlab/ehr_ml/blob/HEAD/ehr_ml/splits.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"47717bef92027d49"}},{"code_sha256_prefix":"fa566175370a3365","entry":"read_split_directory","repo":"som-shahlab/ehr_ml","repo_kind":"listed","path":"ehr_ml/splits.py","file_url":"https://github.com/som-shahlab/ehr_ml/blob/HEAD/ehr_ml/splits.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fa566175370a3365"}},{"code_sha256_prefix":"3324da1a794848b5","entry":"read_time_split","repo":"som-shahlab/ehr_ml","repo_kind":"listed","path":"ehr_ml/splits.py","file_url":"https://github.com/som-shahlab/ehr_ml/blob/HEAD/ehr_ml/splits.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3324da1a794848b5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}