Electronic Medical Records privacy preservation through k-anonymity clustering method

摘要

Electronic Medical Records (EMRs) enable the sharing of patient medical data whenever it is needed and also are used as a tool for building new medical technology and patient recommendation systems. Since EMRs include patients' private data, access is restricted to researchers. Thus, an anonymizing technique is necessary that keeps patients' private data safe while not damaging useful medical information. k-member clustering anonymization approaches k-anonymization as a clustering issue. The objective of the k-member clustering problem is to gather records that will minimize the data distortion during data generalization. Most of the previous clustering techniques include random seed selection. However, randomly selecting a cluster seed will provide inconsistent performance. The authors propose a k-member cluster seed selection algorithm (KMCSSA) that is distinct from the previous clustering methods. Instead of randomly selecting a cluster seed, the proposed method selects the seed based on the closeness centrality to provide consistent information loss (IL) and to reduce the information distortion. An adult database from University of California Irvine Machine Learning Repository was used for the experiment. By comparing the proposed method with two previous methods, the experimental results shows that KMCSSA provides superior performance with respect to information loss. The authors provide a privacy protection algorithm that derives consistent information loss and reduces the overall information distortion.