Virtual Hackathon &
In-Person Co-Working & Demo Day in San Francisco
Purpose
Welcome to Research to the People and Stanford Medicine's Rare Disease AI Hackathon. The purpose of this event series is bringing AI and medical experts together to build open source language models for rare diseases, and create zero-barrier access to rare disease expertise for patients, researchers and physicians. We're excited for the potential AI has to uncover new biomarkers, treatment ideas and novel links between rare diseases. As models are built and tested, this event will also explore validation methods for medical AI. Successful models will be released for further testing and validation on Hypophosphatasia.ai and EhlersDanlos.ai.
Vision
Our vision is to jumpstart an ongoing open source community for rare disease AI models.
Timeline
See Full Calendar on AddEvent!
-
April 2024 Event announced!
-
Asynchronous: Teams work on models. Office hours sessions on training, fine tuning and validating models: Virtual.
-
April 25th: In-person co-working in San Francisco.
-
April 29th: All Hands: Social, Networking, Team Building (Online)
-
TBD: Learn about Ehlers-Danlos Syndrome. Online.
-
TBD: Learn about Hypophosphatasia. Online.
-
TBD: In-person co-working and office hours hosted by Fifty Years.
-
May 15th: Deadline to register your team to be included in the Demo Day.
-
June 17th at 12.00am: Final results due.
-
June 21st 2024: In-Person Demo Day in San Francisco! Open to the public.
-
Post-Hackathon: Models released for Beta testing to broader patient and physician community by Research to the People. Teams will be invited to publish their work in the Research to the People Journal.
Rare Disease Focus
Datasets
Our baseline dataset are publicly available PubMed papers for HPP and EDS. Additional datasets and data sources in the works. *Teams are encouraged to use additional datasets outside of what we provide.* Special thanks to teams who are helping source new datasets to make available for this event! Data downloads available for onboarded teams.
-
Hypophosphatasia - 814 publications.
-
Ehlers Danlos Syndrome. - 1,089 publications.
Problem Tracks
-
Search & Recall: Create a chat interface model for HPP and EDS scientific publications.
-
Discovery: Use additional bio datasets to create a model that can augment research for HPP and EDS, ie: new biomarkers.
Hackathon Events
The bulk of this hackathon will take place virtually, with teams interfacing with AI Researchers, Patients, and Medical experts through virtual and in-person (SF Bay Area) events. The hackathon will focus on fine tune training. The demo day will focus on collective interrogation of the models, especially via doctors, patients and medical experts.
Format
We're doing a rolling start, and welcoming teams to start building models ASAP. Teams can signup and access the data right away to start training their models. Virtual and in-person hackathon events and office hours will be hosted by our team and leading experts leading up to the demo day: June 21st 2024.
Over the course of these events, teams will focus on fine-tuning models with AI and medical experts. This work will culminate in a live demo day pitch session with patients, medical experts, investors and the broader AI and Rare Disease Community.
Demo Day
Our Demo Day will be open to the public. Teams will present live demos of their models and lead a discussion on their approach. This event will feature VC's and investors who are funding generative AI in healthcare and medicine. Note: Models developed for this Hackathon are expected to be open-source. Teams will be able to connect with VC's and Investors for other generative AI projects.
Recommended Tools
Recommended Reading
Purpose
Welcome to Research to the People and Stanford Medicine's Rare Disease AI Hackathon. The purpose of this event series is bringing AI and medical experts together to build open source language models for rare diseases, and create zero-barrier access to rare disease expertise for patients, researchers and physicians. We're excited for the potential AI has to uncover new biomarkers, treatment ideas and novel links between rare diseases. As models are built and tested, this event will also explore validation methods for medical AI. Successful models will be released for further testing and validation on
Hypophosphatasia.ai and EhlersDanlos.ai.
Vision
Our vision is to jumpstart an ongoing open source community for rare disease AI models.
Timeline
Note: Exact dates are still being finalized.
-
March 2024 Event Announced and datasets released.
-
Month/Date/Year: Kick-off event. Teams work on models. Office hours sessions on training, fine tuning and validating models. Virtual and In-person.
-
Month/Date/Year: In-person co-working and office hours hosted by Fifty Years.
-
Month/Date/Year: In-person co-working and office hours hosted at TBD.
-
June 21st 2024: In-Person Demo Day in San Francisco! Open to the public.
-
Ongoing: Models released for Beta testing to broader patient and physician community by Research to the People. Teams will be invited to publish their work in the Research to the People Journal.
Rare Disease Focus
Dataset
Clinical Guidelines and PubMed publications for HPP and EDS. Additional datasets are expected to become available. Data downloads available for onboarded teams.
-
Hypophosphatasia - 814 publications in machine readable format.
-
Ehlers Danlos Syndrome - 216 publications in machine readable format.
Problem
-
Create custom models for Hypophosphatasia and Ehlers Danlos Syndrome.
-
Advanced: Interface the models to create novel research connections between HPP and EDS.
Hackathon Events
The bulk of this hackathon will take place virtually, with teams interfacing with AI Researchers, Patients, and Medical experts through in-person (SF Bay Area) and virtual sessions. This hackathon will focus on:
-
Fine tune training.
-
Doctors, Patients and Medical Experts interrogating models.
-
Advanced: Developing methods for models to interface with each other, creating the possibility of new research links between HPP and EDS.
Format
We're doing a rolling start, and welcoming teams to start building models ASAP. Teams can signup and access the data right away to start training their models. Virtual and in-person hackathon events and office hours will be hosted by our team and leading experts leading up to the demo day: June 21st 2024.
Over the course of these events, teams will focus on fine-tuning models with AI and medical experts. This work will culminate in a live demo day pitch session with patients, medical experts, investors and the broader AI and Rare Disease Community.
Demo Day
Our Demo Day will be open to the public. Teams will present live demos of their models and lead a discussion on their approach. This event will feature VC's and investors who are funding generative AI in healthcare and medicine. Note: Models developed for this Hackathon are expected to be open-source. Teams will be able to connect with VC's and Investors for other generative AI projects.
Recommended Tools
Recommended Reading
Pete Kane
Organizer
Stanford Medicine & Founder of Research to the People.
Stanley Bishop
Organizer
Friendly Neighborhood AI-Scientist. Ex Google.
Jessy Reyes
Organizer
Surgical Tech
Stanford Medicine
Alex Li
Organizer
LLM Scientist, TIFIN, Prev. Cala Health. UC Berkeley Alum.
Ben Busby, PhD
Demo Day MC
Principal Scientist, DNAnexus. Prev. NIH
Organizers
Patient Collaborators
Gigi
Patient Collaborator
HPP & EDS Patient. Grant Writer & RTTP Collaborator.
Sue
Patient Collaborator
Hypophosphatasia Patient Collaborator.
Sam
Patient Collaborator
Citizen Scientist Systems Biologist Patient-Turned-Researcher.
Cortney Gensemer PhD
Patient & Mentor
EDS Researcher; Postdoc, Chip Norris Lab @ MUSC.
@CortDoesScience
More Coming
Michael Snyder, PhD
Advisor
Chair, Stanford Medicine, Genetics and Personalized Medicine.
Lara Bloom
Mentor
President & CEO of The Ehlers-Danlos Society.
Fanny Sie
Mentor
Head of AI & Emerging Technology Collaboration Roche Global Informatics
Katie Link
Mentor
ML Engineer, Hugging Face, ML Research Engineer at NYU Langone Health.
Dr. Woody Gandy
Mentor
Internal Medicine, Board of Directors, Ehlers-Danlos Society.
Bharath Ramsundar, PhD
Mentor
Founder, Deep Forest and Deep Chem. O’Reilly Author. UC Berkeley & Stanford Alum.
David Hall, PhD
Mentor
Research Engineering Lead at
Stanford HAI. Ex. Microsoft. UC Berkeley & Stanford Alum.
Avantika Lal, PhD
Model Evaluator
Principal AI Scientist at Genentech (Roche)
Ex. Insitro, NVIDIA, Stanford Alum.
Liezl Puzon
Mentor
Founder, AI Validation Startup
Ex Facebook NLP Engineer.
Chloe Hsu, PhD
Mentor
ML Scientist.
Ex: Google, Meta,
UC Berkeley, Cal Tech Alum.
RonJon Nag, PhD
Model Evaluator
Inventor, teacher and entrepreneur. Adjunct Professor at Stanford University.
Todd Feinman, MD
Sponsor
Co-Founder and Chief Medical Officer, Dr. Evidence.
Jacob Cole
Mentor
Founder, IdeaFlow.
MIT Alum.
More Coming
Collaborator
Bio Fellow at Fifty Years.
USCF Immunotherapy Scientist.
Nandita Damaraju
Mentor
ML Scientist at Inflammatix. Georgia Tech Alum.
Michael Wornow
Mentor
PhD Candidate, Comp-Sci Stanford. Harvard Alum.
Robert Allaway
Mentor
Principal Scientist, Sage Bionetworks. Dartmouth Alum.
More Coming
Mentor
Advisors, Mentors, & Evaluators
Check us out on:
OpenChallenges.io
Biohackathons.github.io
Backend Engineering
Helping the hackathon and demo day run smoothly!
Rob
Engineering
Founder, Infinite.Tech
Jan Zheng
Engineering
co-Founder, Phage.Direectory
Arzav Jain
Engineering Advisor
Engineer, OpenAI
Stanford University