Clinical Decision Support System for Patient Centric System in Privacy Preserving Way Using Nave Bayesian Classification

Abstract

—A clinical decision support system forms critical capability to link health observations with health knowledge to influence choices by clinicians for improved healthcare. Clinical decision support system, having data mining technique which helps us for extracting data which we want. The clinical decision support system gives us the advantage which of provides the better diagnosis accuracy and also minimize the diagnosis time .The large amounts of clinical data generated every day by many of healthcare system so the naive Bayesian classification can be utilized to formed valuable information to improve clinical decision support system. But the clinical decision support system is quite promising but it also having many challenges about security of patient data. So for that I propose a new privacy-preserving patient centric clinical decision support system, which helps clinician complementary to diagnose the risk of patients disease in a privacy-preserving way. As the past patients historical data are stored in cloud so patient can use it anywhere anytime and used the train naive Bayesian classifier for finding the top-k diseases without leaking any individual patient medical data. Specifically, to protect the privacy of past patients historical data, a new cryptographic tool called additive homomorphism proxy aggregation scheme is designed. Moreover, to leverage the leakage of nave Bayesian classifier, we introduce a privacy-preserving top-k disease names retrieval protocol in our system with document uploading facility. Detailed privacy analysis ensures that patients information is private and will not be leaked out during the disease diagnosis phase. In addition, performance evaluation via extensive simulations also demonstrates that our system can efficiently calculate patients disease risk with high accuracy in a privacy-preserving way.