{"url":"/dataset/mimic-iv-icd-10","name":"MIMIC-IV ICD-10","full_name":null,"description_markdown":"MIMIC-IV ICD-10 contains 122,279 discharge summaries—free-text medical documents—annotated with ICD-10 diagnosis and procedure codes. It contains data for patients admitted to the Beth Israel Deaconess Medical Center emergency department or ICU between 2008-2019. All codes with fewer than ten examples have been removed, and the train-val-test split was created using [multi-label stratified sampling](MIMIC-IV ICD-9). The dataset is described further in [Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study](https://arxiv.org/abs/2304.10909), and the code to use the dataset is found [here](https://github.com/JoakimEdin/medical-coding-reproducibility).\r\n\r\n The dataset is intended for medical code prediction and was created using [MIMIC-IV v2.2](https://physionet.org/content/mimiciv/2.2/) and [MIMIC-IV-NOTE v2.2](https://physionet.org/content/mimic-iv-note/2.2/). Using the two datasets requires a license obtained in [Physionet](https://physionet.org/register/); this can take a couple of days.","description_withheld":null,"homepage":"https://github.com/JoakimEdin/medical-coding-reproducibility","introduced_date":"2023-04-21","introduced_date_note":null,"introduced_by":{"paper":"/paper/automated-medical-coding-on-mimic-iii-and","title":"Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study","first_author":"Joakim Edin","url":null},"license":{"name":"PhysioNet Credentialed Health Data License 1.5.0","url":"https://physionet.org/content/mimiciv/view-license/2.2/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Medical Code Prediction","url":"/task/medical-code-prediction","datasets_with_task":"/datasets/task/medical-code-prediction"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MIMIC-IV ICD-10"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/medical-code-prediction-on-mimic-iv-icd-10","task":"Medical Code Prediction","dataset_variant":"MIMIC-IV ICD-10","rows":6,"metrics":["Precision@8","F1 Macro","F1 Micro","Precision@15","R-Prec","mAP","Exact Match Ratio","AUC Macro","AUC Micro"],"first_row_in_archive_order":{"model":"PLM-ICD","paper":"/paper/automated-medical-coding-on-mimic-iii-and","metrics":{"AUC Macro":"96.6","AUC Micro":"99.2","Exact Match Ratio":"0.4","F1 Macro":"21.1","F1 Micro":"58.5","Precision@15":"55.0","Precision@8":"69.9","R-Prec":"57.9","mAP":"61.9"},"code_links":[{"title":"joakimedin/medical-coding-reproducibility","url":"https://github.com/joakimedin/medical-coding-reproducibility"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/automated-medical-coding-on-mimic-iii-and","title":"Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study","date":"2023-04-21","rows_on_this_dataset":6,"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."}