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 609 genes and 2233 variants with 1749 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.