Important Dates
All deadlines are 11:59PM UTC-12:00 (anywhere on Earth).
| Event |
Date |
| Paper Submission deadline |
Thursday August 21, 2025 |
| Notification of acceptance |
Thursday September 25, 2025 |
| Final versions of papers due |
Monday October 6, 2025 |
| Workshop |
Thursday October 30, 2025 |
Shared Tasks
- Wouncare Visual Question Answering (MEDIQA-WV):
- Asynchronous communication has enabled remote patient care, improving access, and cutting costs. However, with this new care model, the burden for providers increased dramatically. The ability to provide draft responses to remote care patient queries can help speed doctor response and raise care quality. We extend the MEDIQA-M3G 2024 shared task into the domain of wound-care visual question answering. Participants will be tasked with generating a free text response to a patient question and associated images. We created a dataset of questions and answers in English and Chinese. Each question has one or two images and multiple annotations (e.g., anatomic location, wound type).
- Chemotherapy Treatment Event Extraction (2nd edition):
- The Chemotherapy Treatment Timeline Extraction shared task aims to advance the state of the art of clinical event timeline extraction from EHRs, with a focus on chemotherapy event timelines from EHRs of patients with breast, ovarian and skin cancers. The second edition will use the created collection of de-identified EHRs for 57,530 patients with breast and ovarian cancer spanning 2004-2020, and approximately 15,946 patients with melanoma spanning 2010-2020.
- Medical Order Extraction (MEDIQA-OE):
- Medical order extraction involves identifying and structuring various medical orders —such as medications, imaging studies, lab tests, and follow-ups— based on doctor-patient conversations. Previous efforts have focused on extracting entities and relations from clinical texts. This shared task seeks to develop effective solutions for improving clinical documentation, reducing the burden on providers, and ensuring critical patient information is accurately captured from long conversations. The input dialogues are sourced from a combination of existing conversational datasets (e.g., ACI-Bench, PriMock57, NoteChat), and structured lists of medical orders are created by medical annotators.
Prior Events
For content from prior events, please see:
