Preserving Privacy of Patients Based on Re-identification Risk

详细信息    查看全文

• 作者：Himanshu Taneja ; ^{himanshu.taneja24@gmail.com" class="auth_mail" title="E-mail the corresponding author} ; Kapil ^{kapil@nitkkr.ac.in" class="auth_mail" title="E-mail the corresponding author} ; Ashutosh Kumar Singh ^{ashutosh@nitkkr.ac.in" class="auth_mail" title="E-mail the corresponding author}
• 关键词：Big Data ; Cloud Computing ; Electronic Medical Record ; Electronic Health Record ; HealthCare ; k-Anonymity ; l-Diversity ; t-Closeness ; δ-Presence
• 刊名：Procedia Computer Science
• 出版年：2015
• 出版时间：2015
• 年：2015
• 卷：70
• 期：Complete
• 页码：448-454
• 全文大小：400 K

文摘

Electronic Medical Records (EMR) holds the medical data of the patients in an electronic form. It appears as a massive Big Data that needs to be stored in elastic clouds which are generally handled by a third party. The cloud service provider acts as a third party here and have the access to all the EMRs. Also, most of the times, the patient information needs to be shared with other research analysts and medical professionals for research or expert opinion. This raises serious concerns regarding the privacy of the patient's data.

In this paper, an approach based on reducing the re-identification risk is proposed to preserve the privacy of the EMRs. The proposed solution is based on k-Anonymity, l-Diversity, t-Closeness & δ-Presence and is implemented through ARX Anonymization tool. We have implemented the solution on randomly generated medical dataset based on extension of publicly available EMRs. The result shows that the re-identification risks are reduced to 2.33% from 100%.