{"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/ehrxqa-a-multi-modal-question-answering-1","title":"EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images","arxiv_id":"2310.18652","date":"2023-10-28","proceeding":"NeurIPS 2023 11","authors":["Seongsu Bae","Daeun Kyung","Jaehee Ryu","Eunbyeol Cho","Gyubok Lee","Sunjun Kweon","JungWoo Oh","Lei Ji","Eric I-Chao Chang","Tackeun Kim","Edward Choi"],"abstract":"Electronic Health Records (EHRs), which contain patients' medical histories in various multi-modal formats, often overlook the potential for joint reasoning across imaging and table modalities underexplored in current EHR Question Answering (QA) systems. In this paper, we introduce EHRXQA, a novel multi-modal question answering dataset combining structured EHRs and chest X-ray images. To develop our dataset, we first construct two uni-modal resources: 1) The MIMIC-CXR-VQA dataset, our newly created medical visual question answering (VQA) benchmark, specifically designed to augment the imaging modality in EHR QA, and 2) EHRSQL (MIMIC-IV), a refashioned version of a previously established table-based EHR QA dataset. By integrating these two uni-modal resources, we successfully construct a multi-modal EHR QA dataset that necessitates both uni-modal and cross-modal reasoning. To address the unique challenges of multi-modal questions within EHRs, we propose a NeuralSQL-based strategy equipped with an external VQA API. This pioneering endeavor enhances engagement with multi-modal EHR sources and we believe that our dataset can catalyze advances in real-world medical scenarios such as clinical decision-making and research. EHRXQA is available at https://github.com/baeseongsu/ehrxqa.","url_abs":"https://arxiv.org/abs/2310.18652v2","url_pdf":"https://arxiv.org/pdf/2310.18652v2.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":"ehrxqa-a-multi-modal-question-answering-1","repo_url":"https://github.com/baeseongsu/ehrxqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"ehrxqa-a-multi-modal-question-answering-1","repo_url":"https://github.com/baeseongsu/mimic-cxr-vqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"ehrxqa-a-multi-modal-question-answering-1","repo_url":"https://github.com/snoop2head/ehrxqa-2024","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"medical-visual-question-answering","task_name":"Medical Visual Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.18652","atlas_url":"https://app.syntology.ai/?focus=2310.18652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18652"}},"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":"deterministic:regex_extraction","url":"https://github.com/baeseongsu/ehrxqa","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/snoop2head/ehrxqa-2024","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/baeseongsu/mimic-cxr-vqa","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":17,"ran_draft_wrong":2,"ran_fixture":1},"by_repo_kind":{"official":{"samples":12,"ran":12,"repositories":2},"listed":{"samples":8,"ran":8,"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":"6e2a17d1112822e4","entry":"fixed_sincos1d_embeddings","repo":"snoop2head/ehrxqa-2024","repo_kind":"listed","path":"src/modelling_pt.py","file_url":"https://github.com/snoop2head/ehrxqa-2024/blob/HEAD/src/modelling_pt.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6e2a17d1112822e4"}},{"code_sha256_prefix":"15b4480443968277","entry":"fixed_sincos1d_embeddings","repo":"snoop2head/ehrxqa-2024","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/snoop2head/ehrxqa-2024/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"15b4480443968277"}},{"code_sha256_prefix":"f55aa01465579300","entry":"fixed_sincos2d_embeddings","repo":"snoop2head/ehrxqa-2024","repo_kind":"listed","path":"src/modelling_pt.py","file_url":"https://github.com/snoop2head/ehrxqa-2024/blob/HEAD/src/modelling_pt.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f55aa01465579300"}},{"code_sha256_prefix":"26d7ceb9feb979a2","entry":"fixed_sincos2d_embeddings","repo":"snoop2head/ehrxqa-2024","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/snoop2head/ehrxqa-2024/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"26d7ceb9feb979a2"}},{"code_sha256_prefix":"d3faf3a6ebbac897","entry":"format_answer","repo":"baeseongsu/mimic-cxr-vqa","repo_kind":"official","path":"dataset_builder/generate_answer.py","file_url":"https://github.com/baeseongsu/mimic-cxr-vqa/blob/HEAD/dataset_builder/generate_answer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d3faf3a6ebbac897"}},{"code_sha256_prefix":"e29aa95576db1be5","entry":"get_template_pk_to_program_idx","repo":"baeseongsu/mimic-cxr-vqa","repo_kind":"official","path":"dataset_builder/internal_utils/_format_qa_dataset.py","file_url":"https://github.com/baeseongsu/mimic-cxr-vqa/blob/HEAD/dataset_builder/internal_utils/_format_qa_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e29aa95576db1be5"}},{"code_sha256_prefix":"7d221f83f5aed97e","entry":"load_bbox_information","repo":"baeseongsu/mimic-cxr-vqa","repo_kind":"official","path":"dataset_builder/generate_answer.py","file_url":"https://github.com/baeseongsu/mimic-cxr-vqa/blob/HEAD/dataset_builder/generate_answer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d221f83f5aed97e"}},{"code_sha256_prefix":"dd5e458df422425b","entry":"load_database","repo":"baeseongsu/ehrxqa","repo_kind":"official","path":"dataset_builder/generate_answer.py","file_url":"https://github.com/baeseongsu/ehrxqa/blob/HEAD/dataset_builder/generate_answer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd5e458df422425b"}},{"code_sha256_prefix":"b97ea8675949406d","entry":"load_metadata","repo":"baeseongsu/mimic-cxr-vqa","repo_kind":"official","path":"dataset_builder/generate_answer.py","file_url":"https://github.com/baeseongsu/mimic-cxr-vqa/blob/HEAD/dataset_builder/generate_answer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b97ea8675949406d"}},{"code_sha256_prefix":"cd63725ed150c8be","entry":"mask_intersection","repo":"snoop2head/ehrxqa-2024","repo_kind":"listed","path":"src/utils_mae.py","file_url":"https://github.com/snoop2head/ehrxqa-2024/blob/HEAD/src/utils_mae.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cd63725ed150c8be"}},{"code_sha256_prefix":"e0f860b8706ea27b","entry":"mask_not","repo":"snoop2head/ehrxqa-2024","repo_kind":"listed","path":"src/utils_mae.py","file_url":"https://github.com/snoop2head/ehrxqa-2024/blob/HEAD/src/utils_mae.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e0f860b8706ea27b"}},{"code_sha256_prefix":"d049b3e2054cb151","entry":"mask_union","repo":"snoop2head/ehrxqa-2024","repo_kind":"listed","path":"src/utils_mae.py","file_url":"https://github.com/snoop2head/ehrxqa-2024/blob/HEAD/src/utils_mae.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d049b3e2054cb151"}},{"code_sha256_prefix":"75ee7d495c2657a4","entry":"modified_lamb","repo":"snoop2head/ehrxqa-2024","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/snoop2head/ehrxqa-2024/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"75ee7d495c2657a4"}},{"code_sha256_prefix":"d95e69a3370313dc","entry":"post_process_answer","repo":"baeseongsu/ehrxqa","repo_kind":"official","path":"dataset_builder/generate_answer.py","file_url":"https://github.com/baeseongsu/ehrxqa/blob/HEAD/dataset_builder/generate_answer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d95e69a3370313dc"}},{"code_sha256_prefix":"5b629a16609f7161","entry":"post_process_sql","repo":"baeseongsu/ehrxqa","repo_kind":"official","path":"dataset_builder/generate_answer.py","file_url":"https://github.com/baeseongsu/ehrxqa/blob/HEAD/dataset_builder/generate_answer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5b629a16609f7161"}},{"code_sha256_prefix":"93a44f96ae2cca26","entry":"process_sample","repo":"baeseongsu/mimic-cxr-vqa","repo_kind":"official","path":"dataset_builder/internal_utils/_format_qa_dataset.py","file_url":"https://github.com/baeseongsu/mimic-cxr-vqa/blob/HEAD/dataset_builder/internal_utils/_format_qa_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"93a44f96ae2cca26"}},{"code_sha256_prefix":"1971017a9e91dd12","entry":"program_1","repo":"baeseongsu/mimic-cxr-vqa","repo_kind":"official","path":"dataset_builder/program.py","file_url":"https://github.com/baeseongsu/mimic-cxr-vqa/blob/HEAD/dataset_builder/program.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1971017a9e91dd12"}},{"code_sha256_prefix":"d4fec949b3f02995","entry":"program_2","repo":"baeseongsu/mimic-cxr-vqa","repo_kind":"official","path":"dataset_builder/program.py","file_url":"https://github.com/baeseongsu/mimic-cxr-vqa/blob/HEAD/dataset_builder/program.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d4fec949b3f02995"}},{"code_sha256_prefix":"ec654714859fcb55","entry":"program_3","repo":"baeseongsu/mimic-cxr-vqa","repo_kind":"official","path":"dataset_builder/program.py","file_url":"https://github.com/baeseongsu/mimic-cxr-vqa/blob/HEAD/dataset_builder/program.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec654714859fcb55"}},{"code_sha256_prefix":"efbe2b090b9a718d","entry":"split_string","repo":"baeseongsu/mimic-cxr-vqa","repo_kind":"official","path":"dataset_builder/internal_utils/_format_qa_dataset.py","file_url":"https://github.com/baeseongsu/mimic-cxr-vqa/blob/HEAD/dataset_builder/internal_utils/_format_qa_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"efbe2b090b9a718d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}