Securing the medical data using enhanced privacy preserving based blockchain technology in Internet of Things

Now that we live in the digital age, the proliferation of Internet of Things (IoT) strategies raises various design concerns related to privacy for businesses. Patients’ medical data poses an ethical and legal quandary for healthcare organisations, making security a difficult problem to solve. Early studies suggest that blockchain technology could be a substantial answer to the IoT’s data security issues. It is therefore critical to ensure data security when designing a blockchain approach for healthcare applications. A blockchain-based data broadcast strategy with a categorization model in the healthcare industry is proposed in this study. Data from multiple IoT data providers, like blockchain, is used to make secure training algorithms. To ensure a safe and secure learning environment, Homomorphic Encryption (HE) technology is used. The oppositional-based harmony search (OHS) algorithm was used to make the best key for the HE algorithm. For the group of multiple shares of acquired images, a multiple-share creation (MSC) ideal is used. This gives privacy and security to the model. In addition, the blockchain technology is used to transmit data securely to the cloud server, which performs the classification model based on the convolutional neural network to determine the presence of disease. To summarise, the proposed model is known as the OHE-MSC based network, and it employs blockchain technology to create a secure and trustworthy platform for the exchange of data between many data providers using IoT and logging it in a shared ledger. Two benchmark datasets, such as the Breast Cancer Wisconsin Dataset (BCWD) and the Heart Disease Data Set (HDD), are used to evaluate the projected method's performance. Several parts of the simulation showed that the OHE-MSC-based network model achieved better performance than all other approaches. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.