Purpose

Welcome to Stanford Medicine and Research to the People's Rare Disease AI Hackathon. The purpose of this event series is to bring 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 novel links between rare diseases. As models are built and tested, we will also explore validation methods for medical AI models. Our team is excited to jumpstart an open source community for rare disease AI models. Successful models will be released for further testing and validation on Hypophosphatasia.ai and EhlersDanlos.ai.

​

Timeline

• November 2023 Hackathon and Demo Day announced. Datasets released.

• November: Kick-off event. Teams work on models. Office hours sessions on training, fine tuning and validating models. Virtual and In-person.

• December: In-person co-working and office hours hosted by Fifty Years. 

• January: In-person co-working and office hours hosted at TBD. 

• February 2024: In-Person Demo Day! 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

1. Hypophosphatasia.

2. Ehlers Danlos Syndrome.

​Dataset

Clinical Guidelines and the entirety of PubMed publications for HPP and EDS. Additional novel data is expected to become available. Downloads coming soon.

1. Hypophosphatasia [Preprocessed Graph Format] [Raw Data]

2. Ehlers Danlos Syndrome [Preprocessed Graph Format] [Raw Data]

​

Problem

1. Create custom models for Hypophosphatasia and Ehlers Danlos Syndrome.

2. 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:

1. Fine tune training.

2. Doctors, Patients and Medical Experts interrogating models.

3. 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 in February 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

Public Demo Day will be open to the broader AI and Rare Disease Community. 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 the 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

1. Llama 2

2. Run Llama locally with GG.ML

3. HuggingFace

4. LangChain

5. ChromaDB

6. Pinecone

7. Ray

​

Recommended Reading

1. The shaky foundations of large language models and foundation models for electronic health records.

2. Challenges and Applications of Large Language Models.

3. LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers