Task Independent Privacy Preserving Data Mining on Medical Dataset

In this era of data digitization, data mining is essential for getting valuable information. However, privacy and security issues remain major barriers during this process. Since medical records are related to human subjects, privacy protection is taken more seriously than other data mining tasks. As required by the Health Insurance Portability and Accountability Act (HIPAA), it is necessary to protect the privacy of patients and ensure the security of the medical data. The privacy issues are handled by many algorithms and techniques in literature. But, always there exists a trade off between privacy and information. So, to preserve the accuracy of results and to reduce loss of information, task based privacy preserving techniques are developed. Our aim is to implement a task independent technique which preserves the information, privacy and utility of the data. Our algorithm is applied on the original data table to alter only the sensitive raw data before applying any mining methods. The experimental results prove that our simple technique yields excellent results as if worked on the original data set.