Symposium Description
Foundation models are rapidly emerging as powerful tools for solving various biomedical tasks, even with limited task-specific data, while specialist machine learning (ML) models can incorporate clinical domain expertise. Both approaches hold promise for improving patient outcomes and streamlining healthcare administration, but several questions remain: (1) What distinguishes them? (2) What challenges exist in their training and application? (3) How can they seamlessly fit into healthcare routines? (4) What's the best way to regulate these technologies?
Important Dates
- Submission deadline: Jan 5, 2024
- Notification of acceptance: Feb 9, 2024
- Final versions of papers due: Mar 8, 2024
- Symposium: Mar 25, 2024 – Mar 27, 2024
All deadlines are 11:59pm UTC-12:00 (anywhere on Earth)
Relevant topics
Relevant topics for the symposium include, but are not limited to: (1) Clinical foundation model data, pre-training, evaluation, and applications. (2) Innovative ML methods combining healthcare knowledge from physics, biology, and chemistry. (3) Challenges limiting the adoption of ML in healthcare, focusing on usability, trust, robustness, and fairness. (4) New clinical datasets and benchmarks. (5) Regulatory frameworks, ethical considerations, and policy implications of ML for healthcare. (6) Software using foundation models for healthcare challenges, with insights on development and ethics.
Submission Requirements
We invite submissions for two non-archival tracks: Traditional and Non-traditional.
Traditional Track: We seek papers which explore novel approaches or offer fresh insights into the core questions targeted by this symposium. Full papers can be up to 4 pages long with unlimited pages for references and appendices. All submissions undergo a double-blind review, must be anonymized, and should not have been published or under review elsewhere. Nevertheless, authors can later publish their work in other venues due to the symposium's non-archival nature.
Non-traditional Track: We invite all sorts of non-traditional research contributions. This includes papers describing software tools, datasets, benchmarks, clinical abstracts, or previously published research findings that can stimulate insightful discussions among the symposium attendees. These submissions should be up to 2 pages long with unlimited pages for references and appendices. The review process is single-blind. Submissions can be previously published or under review elsewhere, and accepted papers may also be published in other archival venues later.
Submission Site Information
https://openreview.net/group?id=AAAI.org/2024/Spring_Symposium_Series/Cl...
Submission Format: Authors should follow the formatting guidelines outlined in the AAAI-24 Author Kit.
Contact Us
Further details can be found on our symposium website: https://clinicalfoundationmodels.github.io/. Please direct questions to: clinicalfms [at] gmail.com and follow us on Twitter/X at @clinicalfms.
Organizers
- Artur Dubrawski (Carnegie Mellon University)
- Frederic Sala (University of Wisconsin-Madison)
- Gilles Clermont (University of Pittsburgh)
- Jimeng Sun (University of Illinois Urbana-Champaign)
- Su-In Lee (University of Washington)
- Tristan Naumann (Microsoft Research)
- Xinyu (Rachel) Li (Carnegie Mellon University)
- Mononito Goswami (Carnegie Mellon University)