Mining electronic health records and the web for drug repurposing

Kira Radinsky offers an overview of a system that jointly mines 10 years of nation-wide medical records of more than 1.5 million people and extracts medical knowledge from Wikipedia to provide guidance about drug repurposingthe process of applying known drugs in new ways to treat diseases.

Researchers decide on exploratory targets for drug repurposing—the process of applying known drugs in new ways to treat diseases—based on trends in research and observations on small numbers of cases, leading to potentially costly biases of focus and neglect. Kira Radinsky offers an overview of a system that jointly mines 10 years of nationwide medical records of more than 1.5 million people and extracts medical knowledge from Wikipedia to help reduce spurious correlations and provide guidance about drug repurposing. The resulting system seeks to identify potential biological processes to justify potential influences between medications and target diseases via links on a graph constructed from Wikipedia data. Kira shares results of the system on two studies on drug repurposing for hypertension and diabetes. In both cases, the algorithm identified drug families that were previously unknown, and clinical opinion by experts in the field and clinical trials on those drug families suggest that these drugs show promise.