Skip to main content

Graph Search for Healthcare

Jo Prichard (LexisNexis Risk Solutions)
Deal-Flow Salon F
Average rating: ***..
(3.33, 3 ratings)
Slides:   1-PPTX 

Einstein once said “to regard old problems from a new angle requires creative imagination and marks real advances in science."

This presentation will focus on a real life case study and data science experiment using large scale graph analysis to regard old problems from a new angle. The example uses 4 billion relationship between 270 million identities and looks at the social spread of prescription drug abuse and the insights that are gained from this perspective. We will cover how those insights can both be leveraged to disrupt social crime networks and potentially positively affect health outcomes.

It will address some of the challenges and limitations that traditionally made large scale graph analysis extremely difficult and look at how the new breed of open source massively parallel compute platforms reframe and simplify the way graph algorithms are implemented as a data intensive operation.

We will dig into some of the insights gained and showcase how the data has a narrative at a social level that allows unusually social prescriptions to be highlighted, even if each prescription in isolation would have appeared to have been a benign prescription that would not have been flagged individually.

This presentation will specifically cover examples and results on the following topics:

 Interesting social prescription distributions that definitively show the value of these new types of algorithms and measurement.
o Prescription types that show outbreaks of potential fraud waste and abuse or other social issues. (From Hydrocodone to Statins).
o Specific examples of interesting social clusters. Social drug seeking behavior, Prescriber and Pharmacy collusion.
 Flagging prescribers and pharmacies that, for various reasons, are more connected to social outbreaks of interesting social prescription patterns.
 Social prescription density:
o As an indicator of fraud waste and abuse.
o As an indicator of social health issues (such as obesity and/or diabetes).
o To measure potential drug seeking behavior.

How these new social measurements can be leveraged to disrupt networks to tame fraud, waste and abuse along with proactively influencing health outcomes.

Photo of Jo Prichard

Jo Prichard

LexisNexis Risk Solutions

Mr. Prichard is a Data Scientist at LexisNexis Risk Solutions. He focuses on Big Data R&D within LexisNexis for various industries to help customers target fraud, collusion and other red flag social indicates. He has a special interest and experience in applying large scale graph analysis to solve business challenges for companies in the financial services, healthcare, government, insurance and retail sectors. Prior to LexisNexis, Mr. Prichard worked for Topspeed Software R&D in London and was a conference speaker on various aspects of the Clarion programming language.

For exhibition and sponsorship opportunities at Strata Rx conference, contact Sharon Pierce at (203) 304-9476 or spierce@oreilly.com

For information on trade opportunities with O'Reilly conferences email mediapartners
@oreilly.com

View a complete list of Strata Rx 2013 contacts