Pixel-art scene — Stanley stands at the head of a warm hackathon worktable, one hand on his cane, gesturing encouragement to teammates seen from behind under string lights
Rare Disease Active

Undiagnosed Patients Hackathon

International rapid-prototyping hackathon bringing AI, clinicians, and patients together to solve undiagnosed rare disease cases in 48 hours.

rare-diseasehackathondiagnosispatient-driveninternational
Collaborators: Stanford Medicine · Mayo Clinic · Wilhelm Foundation · Karolinska Institute

Some rare diseases are so rare that the person carrying one may be the only documented case on Earth. There's no specialist to refer them to, because the expertise doesn't exist yet — it has to be built, case by case, family by family.

The first Rare Disease AI Hackathon started at Stanford with a concept you could fit on an index card: find the physician heroes doing this near-impossible work, walk up, and ask, "How can I help?" Then assemble small, mixed teams — clinicians, data scientists, patients, engineers — and hand them a real diagnostic case and 48 hours. Small squads. Real problems. Real people waiting on the other end for an answer.

It grew into an international movement. In 2023, the Karolinska Institute in Stockholm hosted the inaugural Undiagnosed Hackathon, delivering four diagnoses from ten families. In 2025, Mayo Clinic hosted 130 collaborators from 28 countries — six diagnoses in 48 hours. Six families who walked in without answers and walked out with a name for what they'd been carrying.

The model works because it quietly inverts the usual power structure. Patients aren't subjects to be studied; they're collaborators who know their own bodies better than anyone else in the room. Clinicians aren't gatekeepers; they're teammates. And the AI tools serve both, accelerating the pattern-matching that human experts do best but can't always do fast enough across a whole genome's worth of possibilities.

Every hackathon teaches us something we didn't know going in. That isn't a side effect — it's the design. The format is built to learn as much as it is to solve, so each event leaves the next one a little sharper, and the whole community a little more able to catch the case that would otherwise have slipped through.

A diagnosis is not a cure. But for a family that has spent years being told "we don't know," a name is where hope gets its footing. That's why the work keeps going — and why the door stays open to anyone, clinician or coder or patient, ready to pull up a chair.