{"url":"/dataset/i2b2-de-identification-dataset","name":"i2b2 De-identification Dataset","full_name":"Informatics for Integrating Biology and the Bedside (i2b2) Project — De-identification Dataset","description_markdown":"This dataset contains 1304 de-identified longitudinal medical records describing 296 patients.","description_withheld":null,"homepage":"https://www.i2b2.org/NLP/DataSets/Main.php","introduced_date":"2015-12-01","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"},{"name":"De-identification","url":"/task/de-identification","datasets_with_task":"/datasets/task/de-identification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["i2b2 De-identification Dataset"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/named-entity-recognition-on-i2b2-de","task":"Named Entity Recognition (NER)","dataset_variant":"i2b2 De-identification Dataset","rows":1,"metrics":["F1","Precision"],"first_row_in_archive_order":{"model":"BiLSTM with ELMo","paper":"/paper/mask-a-flexible-framework-to-facilitate-de","metrics":{"F1":"0.97","Precision":"96"},"code_links":[{"title":"icescentral/MASK_public","url":"https://github.com/icescentral/MASK_public"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mask-a-flexible-framework-to-facilitate-de","title":"MASK: A flexible framework to facilitate de-identification of clinical texts","date":"2020-05-24","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}