Geographic Partitioning Techniques for the Anonymization of Health Care Data

TL;DR

This paper introduces a new geographic data anonymization system for healthcare data using Voronoi diagrams, offering comparable privacy results with faster processing compared to existing methods.

Contribution

A novel health care data anonymization system utilizing Voronoi diagram-based regionalization, improving speed while maintaining data privacy quality.

Findings

Comparable anonymization quality to GeoLeader

Significantly faster processing time

Effective geographic attribute protection

Abstract

Hospitals and health care organizations collect large amounts of detailed health care data that is in high demand by researchers. Thus, the possessors of such data are in need of methods that allow for this data to be released without compromising the confidentiality of the individuals to whom it pertains. As the geographic aspect of this data is becoming increasingly relevant for research being conducted, it is important for an \emph{anonymization} process to pay due attention to the geographic attributes of such data. In this paper, a novel system for health care data anonymization is presented. At the core of the system is the aggregation of an initial regionalization guided by the use of a Voronoi diagram. We conduct a comparison with another geographic-based system of anonymization, GeoLeader. We show that our system is capable of producing results of a comparable quality with a much faster running time.