Abstract submission for SAIL 2025 is now closed. The submission deadline was January 17, 2025 at 11:59 PM Eastern. Accepted Abstracts and Travel Support Awards will be announced February 21, 2025.
We invite submissions for abstracts, which will be selected for podium and poster presentations by the SAIL Program Committee. Abstracts should have a 500-word limit, excluding references, figures, and figure captions, and a maximum of three figures. Abstract submissions are unblinded and can be submitted in any format, and may contain content that has been published within the last 12 months. In addition to being invited to present your work in-person at the symposium, all accepted submissions will also be posted on the SAIL website.
The top abstracts will be selected to give an oral presentation and the top 3 will receive a travel award from NEJM AI.
Abstract Requirements
Abstracts should contain either:
- New and unpublished work, or
- Highlights of recently published work published within the last year.
Work describing pure methods without thoughtful consideration of clinical applicability or implementation, systematic reviews, and perspectives will be considered out of scope and should be submitted elsewhere. Submissions that conduct systematic reviews or apply existing AI methodologies to retrospective data sets, without introducing novel technical approaches or clinical perspectives, are less likely to align with SAIL’s emphasis on deployment.
The ideal submission will use innovative machine learning methodology to address real world clinical problems with results that can be translated to improving healthcare. Submissions that deploy AI models, evaluate deployed models, or develop methods for addressing gaps to deployment (e.g., privacy, interpretability, robustness to dataset shift) are of particular interest. Abstracts should be well supported with references to prior work.
Example research themes include:
- Addressing key challenges in combining AI with clinical workflows, e.g.,
- clinical decision support
- human computer interaction
- interpretability
- active learning
- Deploying intelligent systems at scale, e.g.,
- fairness
- privacy
- generalizability across institutions over time
- real-time prediction
- regulatory compliance
We highly encourage work that involves interdisciplinary collaboration across AI researchers, clinicians, and informaticians.