{"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/de-identification-of-patient-notes-with","title":"De-identification of Patient Notes with Recurrent Neural Networks","arxiv_id":"1606.03475","date":"2016-06-10","proceeding":null,"authors":["Franck Dernoncourt","Ji Young Lee","Ozlem Uzuner","Peter Szolovits"],"abstract":"Objective: Patient notes in electronic health records (EHRs) may contain\ncritical information for medical investigations. However, the vast majority of\nmedical investigators can only access de-identified notes, in order to protect\nthe confidentiality of patients. In the United States, the Health Insurance\nPortability and Accountability Act (HIPAA) defines 18 types of protected health\ninformation (PHI) that needs to be removed to de-identify patient notes. Manual\nde-identification is impractical given the size of EHR databases, the limited\nnumber of researchers with access to the non-de-identified notes, and the\nfrequent mistakes of human annotators. A reliable automated de-identification\nsystem would consequently be of high value.\n  Materials and Methods: We introduce the first de-identification system based\non artificial neural networks (ANNs), which requires no handcrafted features or\nrules, unlike existing systems. We compare the performance of the system with\nstate-of-the-art systems on two datasets: the i2b2 2014 de-identification\nchallenge dataset, which is the largest publicly available de-identification\ndataset, and the MIMIC de-identification dataset, which we assembled and is\ntwice as large as the i2b2 2014 dataset.\n  Results: Our ANN model outperforms the state-of-the-art systems. It yields an\nF1-score of 97.85 on the i2b2 2014 dataset, with a recall 97.38 and a precision\nof 97.32, and an F1-score of 99.23 on the MIMIC de-identification dataset, with\na recall 99.25 and a precision of 99.06.\n  Conclusion: Our findings support the use of ANNs for de-identification of\npatient notes, as they show better performance than previously published\nsystems while requiring no feature engineering.","url_abs":"http://arxiv.org/abs/1606.03475v1","url_pdf":"http://arxiv.org/pdf/1606.03475v1.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":"de-identification-of-patient-notes-with","repo_url":"https://github.com/Franck-Dernoncourt/NeuroNER","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"de-identification","task_name":"De-identification"},{"task_slug":"feature-engineering","task_name":"Feature Engineering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1606.03475","atlas_url":"https://app.syntology.ai/?focus=1606.03475","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.03475"}},"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/Franck-Dernoncourt/NeuroNER","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":11},"by_repo_kind":{"listed":{"samples":11,"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":"c13340f71e587c5b","entry":"bidirectional_LSTM","repo":"Franck-Dernoncourt/NeuroNER","repo_kind":"listed","path":"neuroner/entity_lstm.py","file_url":"https://github.com/Franck-Dernoncourt/NeuroNER/blob/HEAD/neuroner/entity_lstm.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c13340f71e587c5b"}},{"code_sha256_prefix":"571b21d5e0204c30","entry":"get_sentences_and_tokens_from_spacy","repo":"Franck-Dernoncourt/NeuroNER","repo_kind":"listed","path":"neuroner/brat_to_conll.py","file_url":"https://github.com/Franck-Dernoncourt/NeuroNER/blob/HEAD/neuroner/brat_to_conll.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"571b21d5e0204c30"}},{"code_sha256_prefix":"b5925067ab578297","entry":"get_stanford_annotations","repo":"Franck-Dernoncourt/NeuroNER","repo_kind":"listed","path":"neuroner/brat_to_conll.py","file_url":"https://github.com/Franck-Dernoncourt/NeuroNER/blob/HEAD/neuroner/brat_to_conll.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b5925067ab578297"}},{"code_sha256_prefix":"0398487181c48d59","entry":"get_start_and_end_offset_of_token_from_spacy","repo":"Franck-Dernoncourt/NeuroNER","repo_kind":"listed","path":"neuroner/brat_to_conll.py","file_url":"https://github.com/Franck-Dernoncourt/NeuroNER/blob/HEAD/neuroner/brat_to_conll.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0398487181c48d59"}},{"code_sha256_prefix":"4ba9c43926a08fce","entry":"is_token_in_pretrained_embeddings","repo":"Franck-Dernoncourt/NeuroNER","repo_kind":"listed","path":"neuroner/utils_nlp.py","file_url":"https://github.com/Franck-Dernoncourt/NeuroNER/blob/HEAD/neuroner/utils_nlp.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ba9c43926a08fce"}},{"code_sha256_prefix":"224defd09e8e5ea5","entry":"load_pretrained_token_embeddings","repo":"Franck-Dernoncourt/NeuroNER","repo_kind":"listed","path":"neuroner/utils_nlp.py","file_url":"https://github.com/Franck-Dernoncourt/NeuroNER/blob/HEAD/neuroner/utils_nlp.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"224defd09e8e5ea5"}},{"code_sha256_prefix":"0069795317e6d20f","entry":"load_tokens_from_pretrained_token_embeddings","repo":"Franck-Dernoncourt/NeuroNER","repo_kind":"listed","path":"neuroner/utils_nlp.py","file_url":"https://github.com/Franck-Dernoncourt/NeuroNER/blob/HEAD/neuroner/utils_nlp.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0069795317e6d20f"}},{"code_sha256_prefix":"73fc763bfb1aa699","entry":"order_dictionary","repo":"Franck-Dernoncourt/NeuroNER","repo_kind":"listed","path":"neuroner/utils.py","file_url":"https://github.com/Franck-Dernoncourt/NeuroNER/blob/HEAD/neuroner/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"73fc763bfb1aa699"}},{"code_sha256_prefix":"848f9b6b6e76e0bd","entry":"parse_arguments","repo":"Franck-Dernoncourt/NeuroNER","repo_kind":"listed","path":"neuroner/__main__.py","file_url":"https://github.com/Franck-Dernoncourt/NeuroNER/blob/HEAD/neuroner/__main__.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"848f9b6b6e76e0bd"}},{"code_sha256_prefix":"d16e6ce39db7140e","entry":"renamed_load","repo":"Franck-Dernoncourt/NeuroNER","repo_kind":"listed","path":"neuroner/utils.py","file_url":"https://github.com/Franck-Dernoncourt/NeuroNER/blob/HEAD/neuroner/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d16e6ce39db7140e"}},{"code_sha256_prefix":"9c479c5c207423da","entry":"reverse_dictionary","repo":"Franck-Dernoncourt/NeuroNER","repo_kind":"listed","path":"neuroner/utils.py","file_url":"https://github.com/Franck-Dernoncourt/NeuroNER/blob/HEAD/neuroner/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9c479c5c207423da"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}