Treatment regimens are key details in understanding the effects of genetic, epigenetic, and other factors on tumor behavior and responsiveness. As precision oncology progresses, insights into the fine interplay of treatment with tumor molecular characteristics and patient phenotypes becomes even more critical not only as a source of research data, but as a means of translating findings into patient-tailored therapies similar to those that have been applied to breast cancer and melanoma. 

The goal of this task is to build a timeline of Systemic anticancer therapy (SACT) treatment for each patient given all the available Electronic Health Records (EHR) notes of that patient. The notes range the entire spectrum -- primary care provider, oncology, discharge summaries, emergency department, pathology, radiology, etc. Success in completing this task will provide previously unavailable tools for extracting timelines for contextualizing cancer treatment.

Proceeding will be published in the ACL Anthology under  the upcoming ACL Special Interest Group on Clinically Related Language (SIGClinical).

Please note these dates are now final. Thank you for your participation in the task!

April 2, 2025: Registration opens (including Data Use Agreement process)

April 16, 2025: Training and validation data release (see Registration and Data Access on instructions regarding getting access to the data with a signed Data Use Agreement)

July 28, 2025: Test data release date (see information under Data)

July 31, 2025: Run submission deadline

Aug 5, 2025: Release of the results by the organizers

(extended) Aug 21, 2025: Shared task paper submission deadline

(extended) Aug 28, 2025: Reviewers assigned

(extended) Sept 18, 2025: Reviews due

(extended) Sept 25, 2025: Notification of acceptance

(extended) Oct 9, 2025: Final version of papers due

Oct 27-30, 2025: Workshop (Virtual)

Due dates listed above are end of each day (23:59:59), Anywhere on Earth (AoE: UTC-12).

Registration opens: April 2, 2025

To register for the task, please fill out the form. Note that because the data is de-identified EHR notes of real patients, the Principal Investigator (PI) of each team has to sign a Data Use Agreement (DUA).

• Jiarui Yao, Boston Children’s Hospital/Harvard Medical School

• Guergana Savova, Boston Children’s Hospital/Harvard Medical School 

• Harry Hochheiser, University of Pittsburgh

• WonJin Yoon, Boston Children’s Hospital/Harvard Medical School 

• Eli Goldner, Boston Children’s Hospital/Harvard Medical School 

Communication and Contact

For general communications: Please, use our google group chemotimelines2025@googlegroups.com

When joining the group, please indicate your name and affiliation in "Reason for Joining" section.

This forum is a place for any questions you may have about the shared task. Please post your questions here, except in the specific case outlined below, so that all participants can benefit from the information. Any emails sent directly to the organizers regarding the shared task may be shared with the Google group. 

All email regarding data distribution will be sent to your Principal Investigator's email. Please, check that address regularly.

We request you refrain from posting any part of the task data in the google group chemotimelines2025, as it is possible to join the group before the Data Use Agreement (DUA) is fully executed. 

Sensitive inquiries such as DUA, legal issues, data issues (e.g. de-identification), or deadlines can be sent to the organizers mailing list to organizers-chemoTimelines [at] googlegroups.com 

Funding is provided by the United States National Institutes of Health (grants U24CA248010, R01LM010090, R01LM013486, R01LM012973, R01MH126977). The content is solely the responsibility of the authors and does not necessarily represent the official views of the United States National Institutes of Health.

ChemoTimelines 2024

Website: https://sites.google.com/view/chemotimelines2024

Overview paper: Overview of the 2024 Shared Task on Chemotherapy Treatment Timeline Extraction

All Publications: https://aclanthology.org/volumes/2024.clinicalnlp-1/