Preserving the Privacy of Medical Data using Homomorphic Encryption and Prediction of Heart Disease using K-Nearest Neighbor

Abstract

Data is extremely important in today’s world. Data is used in many aspects and hence protecting the data is more important. With a heavier reliance on computers, there are many potential threats to the data stored. Nowadays organizations tend to store and process required computation on the data on the cloud itself without having to maintain it themselves. These cloud services are affordable and easy to use. But to ensure compliance and maintain privacy, the data must be stored in an encrypted format. To ensure privacy of data in the cloud, Homomorphic Encryption can be efficiently used because it allows processing to take place while data is encrypted. This paper presents the technique and design to perform Homomorphic Encryption on the medical dataset for heart disease and applying KNN machine learning algorithm on the encrypted dataset. To provide a more detailed view, we used different algorithms such as Logistic Regression, Naive Bayes, Support Vector Machine, Decision Tree and Random Forest.