MedAI Hackathon 2026
April 10–11, 2026
The inaugural MedAI Hackathon successfully brought together over 230 registrants across the Boston University community, bridging the Charles River Campus and the Medical Campus. The event marked an exciting achievement for convergent research at BU, as participants collaborated in cross-disciplinary teams to develop AI powered solutions for real-world challenges in healthcare and biomedicine.
On Friday, April 10th, participants formed groups of three to six team members, finding collaborators with diverse skillsets and unique perspectives. Going into the full-day event on April 11th, 30 total teams had been created.
The competition featured three distinct problem sets and challenges to select from, all sourced from research groups across BU. The three challenges included:
- Early-stage lung cancer phenotyping, focusing on predicting microscopic vascular invasion in lung resected tissues and pre-surgical biopsies based on digitized images.
- Amyloid PET quantification for Alzheimer’s disease, with the goal of predicting Centiloid scores from amyloid PET images across different radiotracers.
- Acute tubular injury prediction from kidney proteomics data, aiming to predict the presence or absence of acute tubular injury from blood-based protein abundances and clinical covariates.
Participants had the opportunity to tackle any of the three challenges and compete for $10,000 in prize money. On April 11th, the teams reconvened and got started, leveraging tools such as Python, PyTorch, TensorFlow, scikit-learn, JAX, and TerrierGPT on BU-supported stacks.
“The [MedAI] Hackathon demonstrated the power of bringing together students from nearly every corner of BU to solve real biomedical problems through AI,” said Dr. Vijaya Kolachalama, a CBR core faculty member and the lead organizer for the event. “It generated real energy around convergent research and showed how student innovation can feed directly into ongoing scientific work.”
The three teams with the most successful implementations of AI for each challenge track— based on quantitative metrics— were recognized and awarded in the event’s closing ceremony.
Participants in this year’s MedAI Hackathon had the opportunity to gain hands-on experience with real, de-identified data-sets, practice collaboration across disciplines, and make tangible contributions to research.
To learn more about the MedAI Hackathon, visit the event website.