SECURING HEALTHCARE DATA FROM RE-IDENTIFICATION ATTACK USING A HEURISTIC DATA ANONYMIZATION MODEL WITH PRIVACY AND ACCURACY

Main Article Content

Anuradha Devaraj

Abstract

New technologies in healthcare industry provide improved quality of treatment with reduced cost. These technologies deals with the valuable sensitive data and they should be kept safe while we have to maximize their usage. In this paper a novel and efficient data pre-processing method is used which improves the completeness, accuracy and appropriateness of the chosen dataset. The proposed data anonymization method computes different data intervals and replace original sensitive data with computed values. Tests are conducted with a lung cancer dataset, ML algorithms and an existing data anonymization model. The test results show the effectiveness of the model against re-identification attack and the improved accuracy in predicting the lung cancer possibilities.

Downloads

Download data is not yet available.

Article Details

Section
Articles