The Machine Learning for Healthcare Conference (MLHC) is designed for a broad, interdisciplinary audience working at the intersection of machine learning and healthcare. If you’re excited about the promise of machine learning and artificial intelligence (AI) in healthcare, this community brings together AI researchers, clinicians, data scientists, medical informaticians, implementation scientists, industry practitioners, ethicists, and policy experts; regardless of what stage of research you are in, where you come from and what your academic interests are, its a one-stop-shop for figuring out how can we go from idea to practical utility in healthcare. MLHC is particularly well suited for attendees interested in methodologically rigorous ML work grounded in real clinical problems, as well as those aiming to translate ML advances into practice.

Yes. All attendees must register, including authors of accepted papers and abstracts. For accepted submissions, at least one author is required to attend and present the work in person. Registration details, deadlines, and rates are provided on the conference website under the Registration section.

MLHC does not provide housing directly, but the conference website (Program) includes a Travel & Accommodations section with information on recommended hotels, conference rates (when available), and venue details. Attendees are responsible for booking their own travel and lodging.

MLHC offers two tracks:

• Research Track (archival): Full papers presenting novel, generalizable insights in machine learning for healthcare.

• Clinical Abstracts Track (non-archival): Shorter submissions focused on clinical applications, implementation experiences, or real-world impact.

All submissions are handled through OpenReview, and submitting authors for Research Track papers must have active OpenReview profiles by the stated deadlines (for Clinical Abstracts, at least one author must have a profile).

MLHC provides an explicit LLM Use Policy governing how large language models and other generative AI tools may be used in research and writing. Authors are expected to follow this policy carefully, including any disclosure requirements, to ensure transparency, scientific integrity, and reproducibility.

There are several ways to get involved with MLHC, particularly through reviewing and conference organization.

Machine learning reviewers are typically researchers with demonstrated experience publishing at comparable ML or ML+health venues; in practice, this usually means having at least one paper accepted as a first or last author at a peer-reviewed research conference or journal. Reviewers who remain engaged often progress along the service pathway from reviewer → area chair → program committee, and individuals interested in contributing to conference organization in future years are encouraged to express their interest.

Clinical reviewers play a complementary role by providing a clinical perspective on technically oriented submissions. To serve as a clinical reviewer, you should hold an MD degree or be an MD–PhD student, and be interested in evaluating the clinical relevance, feasibility, and potential impact of machine learning research in healthcare settings.

More broadly, the best way to get involved with MLHC is to be an active researcher in the community, whether through submitting work, reviewing, or participating in discussions at the conference.

If you are interested in reviewing or helping with organization and meet the above criteria, please contact the organizers at organizers@mlforhc.org .

MLHC differs in several important ways primarily in the process that drives how research is reviewed, and evaluated. First, the Research Track has archival proceedings, with accepted papers published in the Proceedings of Machine Learning Research (PMLR), making them part of the permanent scholarly record. Second, MLHC follows a machine-learning–style peer review process, including a formal author rebuttal period, during which authors are expected to respond substantively to reviewer feedback. During the rebuttal period they may not make changes to the submission. If their paper is accepted, the authors will have an opportunity to revise their submission in accordance with reviewer feedback. Finally, evaluation emphasizes generalizable insights, methodological rigor, and clarity of ML contributions, rather than solely clinical novelty or outcomes, distinguishing MLHC from many clinically focused meetings.

If you have additional questions, you can contact the organizers at organizers@mlforhc.org.