Behind the Scenes: How Weill Cornell Medicine built a chatbot for clinicians to gain fast access to medical data

Play Behind the Scenes: How Weill Cornell Medicine built a chatbot for clinicians to gain fast access to medical data



Microsoft joined the Englander Institute of Precision Medicine (IPM) at Weill Cornell Medicine for a weeklong hackfest to develop a chatbot that supports both text and voice interactions with the Precision Medicine Knowledgebase (PMKB) for clinical cancer variants and interpretations.

The knowledge base currently supports 163 genes and 518 variants with 404 clinical interpretations. Pathologists and researchers are tasked with accessing this information by clicking through the given portal; however, in an attempt to make the knowledge base more mobile, the team created a bot using the Microsoft Bot Framework that connects to several channels including Microsoft Teams, Skype, Slack, and WebChat. As a result, clinicians can now access this data in many different ways and make life-changing clinical decisions at a faster rate.

Join Jerry Nixon and Heather Shapiro as they welcome Alex Sigaras from Weill Cornell Medicine as they walk us through the project and describe how they built their chatbot using various Microsoft technologies.

  • [01:04] Talk to us a little bit about the Microsoft Bot Framework. What is it and what is it not?
  • [07:25] What are some of the biggest barriers in medicine that are being broken down due to advancements in technology?
  • [11:26] What project did Microsoft and Weill Cornell choose to tackle?
  • [21:02] What was the expectation going into this project? How did it turn out?
  • [28:59] What’s next for you guys?

If you're interested in learning more about the products or solutions discussed in this episode, click on any of the below links for free, in-depth information:

Websites & Blogs:



Right click to download this episode

Download captions

The Discussion

Conversation locked

This conversation has been locked by the site admins. No new comments can be made.