January Meetup: Knowledge Graphs and AI use in Healthcare

💻Start your new years right with PyData Boston! This month, we'll have a talk from the founder of knowledgework.ai Griffin Bishop on knowledge graphs vs embeddings for AI and Lily Xu on using a hybrid traditional/GenAI system at Vertex!

We currently have no food sponsor for this event! Reach out if you're able to sponsor!

RSVP is REQUIRED to attend
Do not arrive before 6:30pm!
📅 Schedule:
6:30–7:00 — Networking
7:00–7:15 — Introduction
7:15–8:15 — Griffin Bishop - Context engineering: Knowledge Graphs vs Embedding RAG
8:15-8:30 - Break
8:30-9:15 — Lily Xu: Traditional AI + LLMs to Automate Complex and Critical Docs in Healthcare
9:15–9:30 — Wrap-up

Speaker: Griffin Bishop (Knowledgework.AI)
Title: Context engineering: Knowledge Graphs vs Embedding RAG
Abstract: Embedding based RAG is often seen as the default choice to power LLM applications: chunk your docs, embed them, cosine similarity your way to relevance. This talk will explain how embeddings often end up much more maintenance intensive than they first seem, and how knowledge graphs can offer a much more understandable, maintainable, and elegant solution to many LLM retrieval problems.

Speaker: Lily Xu (Vertex)
Title: Traditional AI + LLMs to Automate Complex and Critical Docs in Healthcare
Abstract: Informed Consent Forms (ICFs) are critical documents in clinical trials. They are the first, and often most crucial, touchpoint between a patient and a clinical trial study. Yet the process of developing them is laborious, high-stakes, and heavily regulated. Each form must be tailored to jurisdictional requirements and local ethics boards, reviewed by cross-functional teams, and written in plain language that patients can understand. Producing them at scale across countries and disease areas demands manual effort and creates major operational bottlenecks. We used a combination of traditional AI and large language models to autodraft the ICF across clinical trial types, across countries and across disease areas at scale. The build, test, iteration and deployment offers both technical and non technical lessons learned for generative AI applications for complex documents at scale and for meaningful impact.

📍Venue provided by Moderna

This, and all NumFOCUS-affiliated events and spaces, both in-person and online, are governed by a Code of Conduct:
👉 https://pydata.org/code-of-conduct/

⚡⚡**Speak at PyData!**⚡⚡
We are always looking for speakers! Sign up here and we'll be in touch:
🔗 https://forms.gle/kfFZ5hiqA9W57Ewg7

⚡⚡**Sponsor an event!**⚡⚡
PyData events are free and open to all. We’re always looking for sponsors and hosts. Get in touch to support the community:
📧 boston@pydata.org