The US wastes $1.2 trillion dollars on fraud, waste and abuse in healthcare each year. Current approaches to combat fraudulent, wasteful and abusive medical practices involve paying for procedures upfront, followed by retrospective analysis and cost recovery. This “pay-and-chase” method fails in fraud recovery for 95% of cases. Loss prevention is further confounded by the lack of data labeled as fraudulent or wasteful by medical professionals, a necessity for supervised learning approaches.
We address the problems of current methods by implementing a predictive approach that allows a payment organization to intervene before authorization is completed. Marrying the full patient and expansive provider history with real-time physician reporting, we build a model that determines the likelihood of fraud or waste of the current authorization request. The model instantly flags cases that appear anomalous, enabling fraud detection at the time of approval and therefore revolutionizing the traditional “pay-and-chase” approach.
This session is sponsored by EMC
Noah Zimmerman has a background in computer science with training in statistics, immunology and medicine. He completed his doctoral work in Biomedical Informatics at Stanford, where he worked on the development of a blood-based food allergy diagnostic using novel unsupervised statistical learning algorithms. Prior to graduate school, Noah was a member of the founding team of 2 startups in the healthcare/life-science space. In addition to his data scientist duties, he is an instructor at Stanford, teaching a course he co-created in the design school exploring the intersection of science and design. For fun, Noah enjoys snowboarding and hosting a weekly radio show on KZSU Stanford.
For information on exhibition and sponsorship opportunities at the conference, contact Sharon Pierce at (203) 304-9476 or email@example.com
For information on trade opportunities with O'Reilly conferences contact mediapartners
For media-related inquiries, contact Maureen Jennings at firstname.lastname@example.org
View a complete list of Strata Rx contacts