Microsoft forms AI research partnership for precision oncology

As part of Microsoft's Project Hanover, biomedical researchers from the Jackson Laboratory are refining an artificial intelligence tool that "reads" medical documents to inform the development of precision cancer treatments, per an Oct. 27 Microsoft blog post.

The Bar Harbor, Maine-based Jackson Laboratory developed a searchable database of complex genomic information that can be sorted and interpreted to improve outcomes and share information about clinical trials and treatments. To speed this process, the lab's researchers are applying Microsoft's machine reading AI, which automatically extracts from thousands of medical and research documents only the most relevant information about cancer mutations, drugs and patient responses.

The partnership is mutually beneficial: Microsoft's AI tool is increasing the lab team's efficiency in curating their Clinical Knowledgebase, while their usage is simultaneously validating the AI's accuracy and effectiveness in "reading" documents.

"Our goal is to make the human curators superpowered,” said Hoifung Poon, Project Hanover's lead researcher and director of precision health natural language processing with Microsoft's research organization. "With the machine reader, we are able to suggest that this might be a case where a paper is talking about a drug-gene mutation relation that you care about. The curator can look at this in context and, in a couple of minutes, say, 'This is exactly what I want,' or, 'This is incorrect.'"

More articles on AI:
UT Health, Cardinal Health, Amazon Web Services partner on AI medical research
Penn Medicine algorithm flags patients most in need of advance care planning
Microsoft genomics director: The future of healthcare depends on AI

© Copyright ASC COMMUNICATIONS 2019. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.

 

Top 40 Articles from the Past 6 Months