EP06.05 - A Framework for Secure Health Statistical Analysis Methods
e-Health ePoster Library. Samet S. Jun 7, 2016; 131547; EP06.05
Dr. Saeed Samet
Dr. Saeed Samet
Login now to access Regular content available to all registered users.

You may also access this content "anytime, anywhere" with the Free MULTILEARNING App for iOS and Android
Abstract
Rate & Comment (0)
Purpose/Objectives: Health data confidentiality on the level of individuals, enforced by various privacy acts, makes a real barrier to researchers receiving clear, non-anonymized, health information and applying data analytics. On the other hand, releasing anonymized data using various data aggregation and suppression will highly reduce reliability and utility of the released data. Risk of data re-identification is another major drawbacks of data anonymization approach. The main objective of this work is to provide a secure portal for researchers to securely receive the results of their health data queries from two or more health data centres, without violating individuals' data privacy, while the accuracy of the released knowledge is guaranteed and level of data security can be adjusted and measured. Methodology/Approach: Cryptographic techniques and protocols have been used for distributed health statistical analysis methods including Count, Mean, Variance, Standard Deviation, Skewness, Correlation, Chi-Square, Odds Ratio, and Logistic Regression on health data that are collected and stored by two or more healthcare organizations. Two different data settings have been considered; 1- One single data custodian has securely distributed their health data among two or more mediators, such that no proper subset of them being able to reach the original data. 2- Two or more data custodians are possessing original data. Researcher, using the secure portal, can simply create and submit her query to the system. After secure communication and intermediate data exchange among the data custodians, using privacy-preserving building blocks corresponding to the requested query as well as local operations, the final results will be published on the researcher's portal. As a proof of concept, the complete system has been tested over the Digital Epidemiology Chronic Disease Tool (DEPICT) database. This database includes health administrative data from the Canadian Chronic Disease Surveillance System linked with Census between 1998 and 2014 for adults 20 years and older determined to have chronic disease in Newfoundland and Labrador. Finding/Results: A web-based portal is designed, implemented and tested for the protocols using Java programming language. Test data s distributed to two separate parties as data custodians. Performance, accuracy, and security of the system is measured and tested to ensure the applicability of the system on various health information systems with high volume of data. The application can be accessed online by the researchers after registering to the system. The main challenge we face in this approach is the overall performance of the system, when we are dealing with real-time stream big data, in which a huge number of data is entered to the system in short period of time and the researchers need to have real-time results for their queries. Conclusion/Implication/Recommendations: A user-friendly information system on distributed and secured health data, which is accessible online provides a secure portal for both researchers and data custodians to jointly perform health statistical analysis methods. Privacy of the individual health records are preserved, while the researchers are confident on the accuracy, utility and reliability of the received knowledge from the health data owners. 140 Character Summary: An online secure health information system. Helath statistical methods queried from health records stored by multiple data custodians without violating privacy.
    This eLearning portal is powered by:
    This eLearning portal is powered by MULTIEPORTAL
Anonymous User Privacy Preferences

Strictly Necessary Cookies (Always Active)

MULTILEARNING platforms and tools hereinafter referred as “MLG SOFTWARE” are provided to you as pure educational platforms/services requiring cookies to operate. In the case of the MLG SOFTWARE, cookies are essential for the Platform to function properly for the provision of education. If these cookies are disabled, a large subset of the functionality provided by the Platform will either be unavailable or cease to work as expected. The MLG SOFTWARE do not capture non-essential activities such as menu items and listings you click on or pages viewed.


Performance Cookies

Performance cookies are used to analyse how visitors use a website in order to provide a better user experience.


Save Settings