AI for Medicine: A Global Student Hackathon on the Future of Care is an online event hosted by the Open Health AI Collective, designed to address the bottleneck in healthcare where attention is scarce. The challenge invites participants to build AI solutions that help people notice, measure, or act on health problems, rather than adding to the burden.
Who Can Participate The hackathon is open to anyone aged 14 or older who is currently enrolled at an accredited institution. Participants from any field and academic level are welcome. Teams may work alone or consist of up to four members.
The Core Requirement A defining feature of this hackathon is the emphasis on evidence over demonstration: It must be evaluated. Participants must clearly state what they measured, how they measured it, and what the result means. Entries should compare their output against a reference, baseline, or stated cost, and explicitly name the conditions under which the results stop being useful. While missing an Evaluation section does not disqualify an entry, it caps the scores for Technical Depth and Rigor & Reproducibility at half marks each.
Tracks and Prizes Projects are judged across six tracks, with all prizes consisting of signed PDF certificates (no cash value): * Best Overall: Highest combined judging score. * Best Clinical Relevance: Strongest connection to a real care problem. * Best Rigor & Reproducibility: Clearest evaluation and most reproducible work. * Best Novel Data Source: Most useful approach to collecting or using a distinctive data source. * Best Demo: Clearest demonstration of a working project. * People's Choice: Selected by public vote.
All finalists receive a participation certificate, while winners receive track-specific certificates.
Submission Requirements Participants must submit a public repository with a README explaining the project and how to run it, including dependencies and instructions to reproduce the evaluation. Submissions also require a written description covering the problem, method, limitations, potential harm, and future improvements, along with full attribution for all external models, datasets, and code. Projects can be new, in-progress, or previously published, but must run today.
Timeline Submissions are due by Friday, December 4, 2026, at 11:45 PM ET.