PMKB Bot

Microsoft joined the Englander Institute of Precision Medicine (EIPM) at Weill Cornell Medicine to develop a chatbot that supports both text and voice interactions with the Precision Medicine Knowledgebase (PMKB) for clinical cancer variants and interpretations. The PMKB is organized to provide information about clinical cancer variants and interpretations in a structured way, as well as allowing users to submit and edit existing entries for the continued growth of the knowledge base.

The knowledge base currently supports 605 genes and 2124 variants with 1538 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, we 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 access this data in many different ways and make life-changing clinical decisions at a faster rate. Through the use of natural language processing (NLP) within LUIS, we were able to access this data and display it to the user more quickly.

Read the technical case study here.

Press

Team

Olivier Elemento
Olivier Elemento
Director, Englander Institute for Precision Medicine
Andrea Sboner
Andrea Sboner
Director of Informatics and Computational Biology
Alexandros Sigaras
Alexandros Sigaras
Senior Research Associate in Computational Biomedicine

Team members from Microsoft:

  • Heather Shapiro, Technical Evangelist
  • Gavin Bauman, Technical Evangelist
  • Andrew Reitano, Technical Evangelist
Alexandros Sigaras, Heather Shapiro, Gavin Bauman, Michael Mienko and Linda Huang

PMKB Bot Demo