{"url":"/dataset/radgraph","name":"RadGraph","full_name":"RadGraph: Extracting Clinical Entities and Relations from Radiology Reports","description_markdown":"RadGraph is a dataset of entities and relations in radiology reports based on our novel information extraction schema, consisting of 600 reports with 30K radiologist annotations and 221K reports with 10.5M automatically generated annotations.\n\nWe release a development dataset, which contains board-certified radiologist annotations for 500 radiology reports from the MIMIC-CXR dataset (14,579 entities and 10,889 relations), and a test dataset, which contains two independent sets of board-certified radiologist annotations for 100 radiology reports split equally across the MIMIC-CXR and CheXpert datasets. We also release an inference dataset, which contains automatically generated annotations for 220,763 MIMIC-CXR reports (around 6 million entities and 4 million relations) and 500 CheXpert reports (13,783 entities and 9,908 relations) with mappings to associated chest radiographs.","description_withheld":null,"homepage":"","introduced_date":"2021-06-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/radgraph-extracting-clinical-entities-and","title":"RadGraph: Extracting Clinical Entities and Relations from Radiology Reports","first_author":"Saahil Jain","url":null},"license":{"name":"PhysioNet Credentialed Health Data License 1.5.0","url":"https://physionet.org/content/radgraph/view-license/1.0.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Graphs","url":"/datasets/modality/graphs"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Relation Extraction","url":"/task/relation-extraction","datasets_with_task":"/datasets/task/relation-extraction"},{"name":"Joint Entity and Relation Extraction","url":"/task/joint-entity-and-relation-extraction","datasets_with_task":"/datasets/task/joint-entity-and-relation-extraction"},{"name":"Medical Relation Extraction","url":"/task/medical-relation-extraction","datasets_with_task":"/datasets/task/medical-relation-extraction"},{"name":"Medical Named Entity Recognition","url":"/task/medical-named-entity-recognition","datasets_with_task":"/datasets/task/medical-named-entity-recognition"}],"languages":[],"variants":["RadGraph"],"data_loaders":[],"num_papers_in_archive":78,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}