The National Institutes of Health now allows semantic searches of health data repository Medline in a move which could fuel the next big data brekathrough in health. This will enable experts to carry out research based on correlation of readily available medical knowledge.
Brand Niemann, founder of the Federal Big Data Working Group, who is also a former senior enterprise architect and data scientist that the Environmental Protection Agency, applauded the move calling it a “real discovery.”
Big Data infrastructure will now be able to help researchers mine information in published medical data “between therapies and outcomes” which was previously untapped. For instance, as Information Week reports, with graph analysis cancer researchers discovered that in some types of cancer cases, immunotherapy produced better results than chemotherapy.
The Medline database of the National Library of Medicine, stores over 21 million references to medical journal articles from as far back as 1946, with 2,000 to 4,000 new reference additions made five days a week, through 2013. Adding 65 million semantic entries using markup standards has resulted in 2.2 billion Resource Description Framework statements.
This is a lot of under-utilized, semi-structured data waiting to be made sense of within the industry and is now available to researchers.
Read more here.
(Image Credit: Flickr)
