Privacy-Preserving Patient-Centric Clinical Decision Support System on Support Vector Machine

Everyday tremendous amount of medical data is generating. These data needs large amount of space to store and manage. To get the valuable data out of this we need to apply some classification technique. Various data mining techniques are now involving in medical and health care field to solve this issue. These data mining techniques help the clinician to diagnosis the disease risk. In recent year, Clinical decision support system gained attention due to its advantages as improving diagnosis accuracy and reducing diagnosis time. The method described in this paper supports clinician complementary to diagnose the risk of patients’ disease in a privacy-preserving way. Patient’s historical data is stored on the cloud and is used to train the Support Vector Machine (SVM) classifiers and trained classifier is used to calculate disease risk. To prevent patients clinical sensitive data, all data is stored and processed in encrypted format. We have proposed homomorphic encryption technique. Pailier encryption algorithm is used to encrypt clinical sensitive data.