Secure Block Chain-Based Healthcare Sensitive Data Prediction Using Pragmatic Quasi-Identifiers in a Decentralized Cloud Environment

Security is essential for all facts, information sharing around the internet and maintaining personalized information. In recent days, the healthcare industry needs privacy-preserving to keep personalized data from others containing sensitive information. Due to increasing security breaches, fundamental sharing problems with personalized details shared on the internet lead to security problems. To resolve this problem, we propose a Secure Blockchain-based Healthcare-sensitive data prediction using a Pragmatic quasi identifier in a decentralized cloud environment. Pragmatic quasi-sensitivity Identification (PQSI) based Privacy-preserving for securing personalized records Using Hyper Recurrent feature classification for improved cloud security. Initially, the sensitivity fitness value of the feature is estimated through Intensive feature success rate (IFSR) and clustered by marginal subset features. By marginalizing the sensitivity threshold frequency rate, the components are extracted by pragmatic quasi-sensitive identifier and classified using Hyper recurrent Neural classification (HRNC) to find the sensitive and non-sensitive records based on frequency fitness weight to split and store perception as individually in the private cloud. Further, to improve the security level Elliptic Curve Cryptography (ECC) based master node authentication technique is used in the blockchain concept. Peer end Block chain principle is applied to secure the sensitive data. To ensure the sensitive records are sanitized into data blocks to assure in a blockchain environment. This proposed system produces higher prediction accuracy than other methods and achieves higher sensitivity and specificity rate performance.