AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images

Seongsu Bae, Daeun Kyung, Jaehee Ryu, Eunbyeol Cho, Gyubok Lee, Sunjun Kweon, Jungwoo Oh, Lei Ji, Eric I-Chao Chang, Tackeun Kim, Edward Choi

NeurIPS 2023 · Vision-language and multimodal › Visual question answering · approach: Universal VQA models · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Pre-train the PubMedCLIP model on the shared MIMIC-CXR image-report corpusPubMedCLIP on MIMIC-CXR-VQA · MIMIC-CXR-VQA testaccuracy: $54.9 \pm 1.3$ -> $56.5 \pm 2.1$Improved
Pre-train MedViLL on the shared MIMIC-CXR image-report corpusMedViLL on MIMIC-CXR-VQA · MIMIC-CXR-VQA testaccuracy: 63.6 -> 63.6Improved
Pre-train M³AE on the shared MIMIC-CXR image-report corpusM³AE on MIMIC-CXR-VQA · MIMIC-CXR-VQA testaccuracy: $68.9 \pm 0.3$ -> $69.2 \pm 0.4$Improved
Retrieve question-specific few-shot examples with BM25 instead of using a fixed promptChatGPT + M³AE on EHRXQA · Image-related QAAcc_EX|pred: 17.4 -> 48.2Improved
Retrieve question-specific few-shot examples with BM25 instead of using a fixed promptChatGPT + M³AE on EHRXQA · Table-related QAAcc_EX|pred: 30.0 -> 92.9Improved
Retrieve question-specific few-shot examples with BM25 instead of using a fixed promptChatGPT + M³AE on EHRXQA · Image+Table-related QAAcc_EX|pred: 35.7 -> 65.9Improved
Require the VQA model to process multiple images for a single-patient questionChatGPT + M³AE on EHRXQA · Image-related, single-patient N-image scopeAcc_EX|pred: 48.2 -> 39.6Hurt
Expand image-based QA from a patient scope to a group scopeChatGPT + M³AE on EHRXQA · Image-related group scopeAcc_EX|pred: 48.2 -> 1.7Hurt
Constrain the image scope with table conditions in combined-modality questionsChatGPT + M³AE on EHRXQA · Image+Table-related versus Image-related QAAcc_EX|pred: 48.2 -> 65.9Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy