{"url":"/dataset/radqa","name":"RadQA","full_name":"A Question Answering Dataset to Improve Comprehension of Radiology Reports","description_markdown":"RadQA is a radiology question answering dataset with 3074 questions posed against radiology reports and annotated with their corresponding answer spans (resulting in a total of 6148 question-answer evidence pairs) by physicians. The questions are manually created using the clinical referral section of the reports that take into account the actual information needs of ordering physicians and eliminate bias from seeing the answer context (and, further, organically create unanswerable questions). The answer spans are marked within the Findings and Impressions sections of a report. The dataset aims to satisfy the complex clinical requirements by including complete (yet concise) answer phrases (which are not just entities) that can span multiple lines.","description_withheld":null,"homepage":"https://github.com/krobertslab/datasets/tree/master/radqa","introduced_date":"2022-06-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/radqa-a-question-answering-dataset-to-improve","title":"RadQA: A Question Answering Dataset to Improve Comprehension of Radiology Reports","first_author":"Sarvesh Soni","url":null},"license":{"name":"PhysioNet Credentialed Health Data License 1.5.0","url":"https://physionet.org/content/radqa/view-license/1.0.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["RadQA"],"data_loaders":[],"num_papers_in_archive":9,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/reading-comprehension-on-radqa","task":"Reading Comprehension","dataset_variant":"RadQA","rows":1,"metrics":["Answer F1"],"first_row_in_archive_order":{"model":"BERT pretrained on MIMIC-III","paper":"/paper/radqa-a-question-answering-dataset-to-improve","metrics":{"Answer F1":"63.55"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/radqa-a-question-answering-dataset-to-improve","title":"RadQA: A Question Answering Dataset to Improve Comprehension of Radiology Reports","date":"2022-06-01","rows_on_this_dataset":1,"code_links":0,"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."}