How the Heritage Health Prize data was de-identified

Date:  March 6th,2012 from 12pm to 1pm EST

The Heritage Health Prize (HHP) is one of the largest health analytics competitions that has been run to date. The objective is to construct a model to predict the number of days that a patient will be in hospital. The core data set consisted of claims information on 113,000 patients over a three year period.  Before such data can be made available to a large and international pool of entrants, it is necessary to de-identify the data and ensure that it meets the requirements in the US Health Insurance Portability and Accountability Act (HIPAA) Privacy Rule. In this webinar we describe the considerations and tradeoffs that went into the de-identification of the HHP data set, the metrics that were used to evaluate re-identification risk, the attacks considered, and the de-identification methods used. It is an example of how to manage re-identification risk and still allow the disclosure of a large health data set, but also highlights the practical issues that need to be accounted for when dealing with health information. The presenter was the lead of the team that performed the de-identification of this data set.

Speaker:  Khaled El Emam, CHEO Research Institute

Biography:   Dr. Khaled El Emam is an Associate Professor at the University of Ottawa, Faculty of Medicine, a senior investigator at the Children’s Hospital of Eastern Ontario Research Institute, and a Canada Research Chair in Electronic Health Information at the University of Ottawa. His main area of research is developing techniques for health data anonymization and secure disease surveillance for public health purposes. Previously Khaled was a Senior Research Officer at the National Research Council of Canada, and prior to that he was head of the Quantitative Methods Group at the Fraunhofer Institute in Kaiserslautern, Germany. He has co-founded two companies to commercialize the results of his research work. In 2003 and 2004, he was ranked as the top systems and software engineering scholar worldwide by the Journal of Systems and Software based on his research on measurement and quality evaluation and improvement, and ranked second in 2002 and 2005. He holds a Ph.D. from the Department of Electrical and Electronics, King’s College, at the University of London (UK).

Download the slides here.

Link to to the article can be found here.